Visible to the public Biblio

Found 298 results

Filters: Keyword is Deep Learning  [Clear All Filters]
2021-08-02
Peng, Ye, Fu, Guobin, Luo, Yingguang, Yu, Qi, Li, Bin, Hu, Jia.  2020.  A Two-Layer Moving Target Defense for Image Classification in Adversarial Environment. 2020 IEEE 6th International Conference on Computer and Communications (ICCC). :410—414.
Deep learning plays an increasingly important role in various fields due to its superior performance, and it also achieves advanced recognition performance in the field of image classification. However, the vulnerability of deep learning in the adversarial environment cannot be ignored, and the prediction result of the model is likely to be affected by the small perturbations added to the samples by the adversary. In this paper, we propose a two-layer dynamic defense method based on defensive techniques pool and retrained branch model pool. First, we randomly select defense methods from the defense pool to process the input. The perturbation ability of the adversarial samples preprocessed by different defense methods changed, which would produce different classification results. In addition, we conduct adversarial training based on the original model and dynamically generate multiple branch models. The classification results of these branch models for the same adversarial sample is inconsistent. We can detect the adversarial samples by using the inconsistencies in the output results of the two layers. The experimental results show that the two-layer dynamic defense method we designed achieves a good defense effect.
2021-07-28
Vinzamuri, Bhanukiran, Khabiri, Elham, Bhamidipaty, Anuradha, Mckim, Gregory, Gandhi, Biren.  2020.  An End-to-End Context Aware Anomaly Detection System. 2020 IEEE International Conference on Big Data (Big Data). :1689—1698.
Anomaly detection (AD) is very important across several real-world problems in the heavy industries and Internet-of-Things (IoT) domains. Traditional methods so far have categorized anomaly detection into (a) unsupervised, (b) semi-supervised and (c) supervised techniques. A relatively unexplored direction is the development of context aware anomaly detection systems which can build on top of any of these three techniques by using side information. Context can be captured from a different modality such as semantic graphs encoding grouping of sensors governed by the physics of the asset. Process flow diagrams of an operational plant depicting causal relationships between sensors can also provide useful context for ML algorithms. Capturing such semantics by itself can be pretty challenging, however, our paper mainly focuses on, (a) designing and implementing effective anomaly detection pipelines using sparse Gaussian Graphical Models with various statistical distance metrics, and (b) differentiating these pipelines by embedding contextual semantics inferred from graphs so as to obtain better KPIs in practice. The motivation for the latter of these two has been explained above, and the former in particular is well motivated by the relatively mediocre performance of highly parametric deep learning methods for small tabular datasets (compared to images) such as IoT sensor data. In contrast to such traditional automated deep learning (AutoAI) techniques, our anomaly detection system is based on developing semantics-driven industry specific ML pipelines which perform scalable computation evaluating several models to identify the best model. We benchmark our AD method against state-of-the-art AD techniques on publicly available UCI datasets. We also conduct a case study on IoT sensor and semantic data procured from a large thermal energy asset to evaluate the importance of semantics in enhancing our pipelines. In addition, we also provide explainable insights for our model which provide a complete perspective to a reliability engineer.
2021-07-27
Kim, Hyeji, Jiang, Yihan, Kannan, Sreeram, Oh, Sewoong, Viswanath, Pramod.  2020.  Deepcode: Feedback Codes via Deep Learning. IEEE Journal on Selected Areas in Information Theory. 1:194—206.
The design of codes for communicating reliably over a statistically well defined channel is an important endeavor involving deep mathematical research and wide-ranging practical applications. In this work, we present the first family of codes obtained via deep learning, which significantly outperforms state-of-the-art codes designed over several decades of research. The communication channel under consideration is the Gaussian noise channel with feedback, whose study was initiated by Shannon; feedback is known theoretically to improve reliability of communication, but no practical codes that do so have ever been successfully constructed. We break this logjam by integrating information theoretic insights harmoniously with recurrent-neural-network based encoders and decoders to create novel codes that outperform known codes by 3 orders of magnitude in reliability and achieve a 3dB gain in terms of SNR. We also demonstrate several desirable properties of the codes: (a) generalization to larger block lengths, (b) composability with known codes, and (c) adaptation to practical constraints. This result also has broader ramifications for coding theory: even when the channel has a clear mathematical model, deep learning methodologies, when combined with channel-specific information-theoretic insights, can potentially beat state-of-the-art codes constructed over decades of mathematical research.
2021-07-08
Li, Sichun, Jin, Xin, Yao, Sibing, Yang, Shuyu.  2020.  Underwater Small Target Recognition Based on Convolutional Neural Network. Global Oceans 2020: Singapore – U.S. Gulf Coast. :1—7.
With the increasingly extensive use of diver and unmanned underwater vehicle in military, it has posed a serious threat to the security of the national coastal area. In order to prevent the underwater diver's impact on the safety of water area, it is of great significance to identify underwater small targets in time to make early warning for it. In this paper, convolutional neural network is applied to underwater small target recognition. The recognition targets are diver, whale and dolphin. Due to the time-frequency spectrum can reflect the essential features of underwater target, convolutional neural network can learn a variety of features of the acoustic signal through the image processed by the time-frequency spectrum, time-frequency image is input to convolutional neural network to recognize the underwater small targets. According to the study of learning rate and pooling mode, the network parameters and structure suitable for underwater small target recognition in this paper are selected. The results of data processing show that the method can identify underwater small targets accurately.
2021-06-28
Wei, Wenqi, Liu, Ling, Loper, Margaret, Chow, Ka-Ho, Gursoy, Mehmet Emre, Truex, Stacey, Wu, Yanzhao.  2020.  Adversarial Deception in Deep Learning: Analysis and Mitigation. 2020 Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA). :236–245.
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threats to a range of mission-critical deep learning systems and applications. This paper takes a holistic view to characterize the adversarial examples in deep learning by studying their adverse effect and presents an attack-independent countermeasure with three original contributions. First, we provide a general formulation of adversarial examples and elaborate on the basic principle for adversarial attack algorithm design. Then, we evaluate 15 adversarial attacks with a variety of evaluation metrics to study their adverse effects and costs. We further conduct three case studies to analyze the effectiveness of adversarial examples and to demonstrate their divergence across attack instances. We take advantage of the instance-level divergence of adversarial examples and propose strategic input transformation teaming defense. The proposed defense methodology is attack-independent and capable of auto-repairing and auto-verifying the prediction decision made on the adversarial input. We show that the strategic input transformation teaming defense can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false-positive rates, compared to existing representative defense methods.
Lee, Hyunjun, Bere, Gomanth, Kim, Kyungtak, Ochoa, Justin J., Park, Joung-hu, Kim, Taesic.  2020.  Deep Learning-Based False Sensor Data Detection for Battery Energy Storage Systems. 2020 IEEE CyberPELS (CyberPELS). :1–6.
Battery energy storage systems are facing risks of unreliable battery sensor data which might be caused by sensor faults in an embedded battery management system, communication failures, and even cyber-attacks. It is crucial to evaluate the trustworthiness of battery sensor data since inaccurate sensor data could lead to not only serious damages to battery energy storage systems, but also threaten the overall reliability of their applications (e.g., electric vehicles or power grids). This paper introduces a battery sensor data trust framework enabling detecting unreliable data using a deep learning algorithm. The proposed sensor data trust mechanism could potentially improve safety and reliability of the battery energy storage systems. The proposed deep learning-based battery sensor fault detection algorithm is validated by simulation studies using a convolutional neural network.
2021-06-24
Habib ur Rehman, Muhammad, Mukhtar Dirir, Ahmed, Salah, Khaled, Svetinovic, Davor.  2020.  FairFed: Cross-Device Fair Federated Learning. 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR). :1–7.
Federated learning (FL) is the rapidly developing machine learning technique that is used to perform collaborative model training over decentralized datasets. FL enables privacy-preserving model development whereby the datasets are scattered over a large set of data producers (i.e., devices and/or systems). These data producers train the learning models, encapsulate the model updates with differential privacy techniques, and share them to centralized systems for global aggregation. However, these centralized models are always prone to adversarial attacks (such as data-poisoning and model poisoning attacks) due to a large number of data producers. Hence, FL methods need to ensure fairness and high-quality model availability across all the participants in the underlying AI systems. In this paper, we propose a novel FL framework, called FairFed, to meet fairness and high-quality data requirements. The FairFed provides a fairness mechanism to detect adversaries across the devices and datasets in the FL network and reject their model updates. We use a Python-simulated FL framework to enable large-scale training over MNIST dataset. We simulate a cross-device model training settings to detect adversaries in the training network. We used TensorFlow Federated and Python to implement the fairness protocol, the deep neural network, and the outlier detection algorithm. We thoroughly test the proposed FairFed framework with random and uniform data distributions across the training network and compare our initial results with the baseline fairness scheme. Our proposed work shows promising results in terms of model accuracy and loss.
Dang, Tran Khanh, Truong, Phat T. Tran, Tran, Pi To.  2020.  Data Poisoning Attack on Deep Neural Network and Some Defense Methods. 2020 International Conference on Advanced Computing and Applications (ACOMP). :15–22.
In recent years, Artificial Intelligence has disruptively changed information technology and software engineering with a proliferation of technologies and applications based-on it. However, recent researches show that AI models in general and the most greatest invention since sliced bread - Deep Learning models in particular, are vulnerable to being hacked and can be misused for bad purposes. In this paper, we carry out a brief review of data poisoning attack - one of the two recently dangerous emerging attacks - and the state-of-the-art defense methods for this problem. Finally, we discuss current challenges and future developments.
2021-05-25
Meghdouri, Fares, Vázquez, Félix Iglesias, Zseby, Tanja.  2020.  Cross-Layer Profiling of Encrypted Network Data for Anomaly Detection. 2020 IEEE 7th International Conference on Data Science and Advanced Analytics (DSAA). :469—478.

In January 2017 encrypted Internet traffic surpassed non-encrypted traffic. Although encryption increases security, it also masks intrusions and attacks by blocking the access to packet contents and traffic features, therefore making data analysis unfeasible. In spite of the strong effect of encryption, its impact has been scarcely investigated in the field. In this paper we study how encryption affects flow feature spaces and machine learning-based attack detection. We propose a new cross-layer feature vector that simultaneously represents traffic at three different levels: application, conversation, and endpoint behavior. We analyze its behavior under TLS and IPSec encryption and evaluate the efficacy with recent network traffic datasets and by using Random Forests classifiers. The cross-layer multi-key approach shows excellent attack detection in spite of TLS encryption. When IPsec is applied, the reduced variant obtains satisfactory detection for botnets, yet considerable performance drops for other types of attacks. The high complexity of network traffic is unfeasible for monolithic data analysis solutions, therefore requiring cross-layer analysis for which the multi-key vector becomes a powerful profiling core.

2021-05-20
Yu, Jia ao, Peng, Lei.  2020.  Black-box Attacks on DNN Classifier Based on Fuzzy Adversarial Examples. 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP). :965—969.
The security of deep learning becomes increasing important with the more and more related applications. The adversarial attack is the known method that makes the performance of deep learning network (DNN) decline rapidly. However, adversarial attack needs the gradient knowledge of the target networks to craft the specific adversarial examples, which is the white-box attack and hardly becomes true in reality. In this paper, we implement a black-box attack on DNN classifier via a functionally equivalent network without knowing the internal structure and parameters of the target networks. And we increase the entropy of the noise via deep convolution generative adversarial networks (DCGAN) to make it seems fuzzier, avoiding being probed and eliminated easily by adversarial training. Experiments show that this method can produce a large number of adversarial examples quickly in batch and the target network cannot improve its accuracy via adversarial training simply.
2021-05-18
Niloy, Nishat Tasnim, Islam, Md. Shariful.  2020.  IntellCache: An Intelligent Web Caching Scheme for Multimedia Contents. 2020 Joint 9th International Conference on Informatics, Electronics Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision Pattern Recognition (icIVPR). :1–6.
The traditional reactive web caching system is getting less popular day by day due to its inefficiency in handling the overwhelming requests for multimedia content. An intelligent web caching system intends to take optimal cache decisions by predicting future popular contents (FPC) proactively. In recent years, a few approaches have proposed some intelligent caching system where they were concerned about proactive caching. Those works intensified the importance of FPC prediction using the prediction models. However, only FPC prediction may not help to get the optimal solution in every scenario. In this paper, a technique named IntellCache has been proposed that increases the caching efficiency by taking a cache decision i.e. content storing decision before storing the predicted FPC. Different deep learning models such as- multilayer perceptron (MLP), Long short-term memory (LSTM) of Recurrent Neural Network (RNN) and ConvLSTM a combination of LSTM and Convolutional Neural Network (CNN) are compared to identify the most efficient model for FPC. The information on the contents of 18 years from the MovieLens data repository has been mined to evaluate the proposed approach. Results show that this proposed scheme outperforms previous solutions by achieving a higher cache hit ratio and lower average delay and thus, ensures users' satisfaction.
Fidalgo, Ana, Medeiros, Ibéria, Antunes, Paulo, Neves, Nuno.  2020.  Towards a Deep Learning Model for Vulnerability Detection on Web Application Variants. 2020 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW). :465–476.
Reported vulnerabilities have grown significantly over the recent years, with SQL injection (SQLi) being one of the most prominent, especially in web applications. For these, such increase can be explained by the integration of multiple software parts (e.g., various plugins and modules), often developed by different organizations, composing thus web application variants. Machine Learning has the potential to be a great ally on finding vulnerabilities, aiding experts by reducing the search space or even by classifying programs on their own. However, previous work usually does not consider SQLi or utilizes techniques hard to scale. Moreover, there is a clear gap in vulnerability detection with machine learning for PHP, the most popular server-side language for web applications. This paper presents a Deep Learning model able to classify PHP slices as vulnerable (or not) to SQLi. As slices can belong to any variant, we propose the use of an intermediate language to represent the slices and interpret them as text, resorting to well-studied Natural Language Processing (NLP) techniques. Preliminary results of the use of the model show that it can discover SQLi, helping programmers and precluding attacks that would eventually cost a lot to repair.
Zheng, Wei, Gao, Jialiang, Wu, Xiaoxue, Xun, Yuxing, Liu, Guoliang, Chen, Xiang.  2020.  An Empirical Study of High-Impact Factors for Machine Learning-Based Vulnerability Detection. 2020 IEEE 2nd International Workshop on Intelligent Bug Fixing (IBF). :26–34.
Ahstract-Vulnerability detection is an important topic of software engineering. To improve the effectiveness and efficiency of vulnerability detection, many traditional machine learning-based and deep learning-based vulnerability detection methods have been proposed. However, the impact of different factors on vulnerability detection is unknown. For example, classification models and vectorization methods can directly affect the detection results and code replacement can affect the features of vulnerability detection. We conduct a comparative study to evaluate the impact of different classification algorithms, vectorization methods and user-defined variables and functions name replacement. In this paper, we collected three different vulnerability code datasets. These datasets correspond to different types of vulnerabilities and have different proportions of source code. Besides, we extract and analyze the features of vulnerability code datasets to explain some experimental results. Our findings from the experimental results can be summarized as follows: (i) the performance of using deep learning is better than using traditional machine learning and BLSTM can achieve the best performance. (ii) CountVectorizer can improve the performance of traditional machine learning. (iii) Different vulnerability types and different code sources will generate different features. We use the Random Forest algorithm to generate the features of vulnerability code datasets. These generated features include system-related functions, syntax keywords, and user-defined names. (iv) Datasets without user-defined variables and functions name replacement will achieve better vulnerability detection results.
2021-05-13
Gomathi, S., Parmar, Nilesh, Devi, Jyoti, Patel, Namrata.  2020.  Detecting Malware Attack on Cloud using Deep Learning Vector Quantization. 2020 12th International Conference on Computational Intelligence and Communication Networks (CICN). :356—361.

In recent times cloud services are used widely and due to which there are so many attacks on the cloud devices. One of the major attacks is DDos (distributed denial-of-service) -attack which mainly targeted the Memcached which is a caching system developed for speeding the websites and the networks through Memcached's database. The DDoS attack tries to destroy the database by creating a flood of internet traffic at the targeted server end. Attackers send the spoofing applications to the vulnerable UDP Memcached server which even manipulate the legitimate identity of the sender. In this work, we have proposed a vector quantization approach based on a supervised deep learning approach to detect the Memcached attack performed by the use of malicious firmware on different types of Cloud attached devices. This vector quantization approach detects the DDoas attack performed by malicious firmware on the different types of cloud devices and this also classifies the applications which are vulnerable to attack based on cloud-The Hackbeased services. The result computed during the testing shows the 98.2 % as legally positive and 0.034% as falsely negative.

Feng, Xiaohua, Feng, Yunzhong, Dawam, Edward Swarlat.  2020.  Artificial Intelligence Cyber Security Strategy. 2020 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech). :328—333.
Nowadays, STEM (science, technology, engineering and mathematics) have never been treated so seriously before. Artificial Intelligence (AI) has played an important role currently in STEM. Under the 2020 COVID-19 pandemic crisis, coronavirus disease across over the world we are living in. Every government seek advices from scientist before making their strategic plan. Most of countries collect data from hospitals (and care home and so on in the society), carried out data analysis, using formula to make some AI models, to predict the potential development patterns, in order to make their government strategy. AI security become essential. If a security attack make the pattern wrong, the model is not a true prediction, that could result in thousands life loss. The potential consequence of this non-accurate forecast would be even worse. Therefore, take security into account during the forecast AI modelling, step-by-step data governance, will be significant. Cyber security should be applied during this kind of prediction process using AI deep learning technology and so on. Some in-depth discussion will follow.AI security impact is a principle concern in the world. It is also significant for both nature science and social science researchers to consider in the future. In particular, because many services are running on online devices, security defenses are essential. The results should have properly data governance with security. AI security strategy should be up to the top priority to influence governments and their citizens in the world. AI security will help governments' strategy makers to work reasonably balancing between technologies, socially and politics. In this paper, strategy related challenges of AI and Security will be discussed, along with suggestions AI cyber security and politics trade-off consideration from an initial planning stage to its near future further development.
S, Naveen, Puzis, Rami, Angappan, Kumaresan.  2020.  Deep Learning for Threat Actor Attribution from Threat Reports. 2020 4th International Conference on Computer, Communication and Signal Processing (ICCCSP). :1–6.
Threat Actor Attribution is the task of identifying an attacker responsible for an attack. This often requires expert analysis and involves a lot of time. There had been attempts to detect a threat actor using machine learning techniques that use information obtained from the analysis of malware samples. These techniques will only be able to identify the attack, and it is trivial to guess the attacker because various attackers may adopt an attack method. A state-of-the-art method performs attribution of threat actors from text reports using Machine Learning and NLP techniques using Threat Intelligence reports. We use the same set of Threat Reports of Advanced Persistent Threats (APT). In this paper, we propose a Deep Learning architecture to attribute Threat actors based on threat reports obtained from various Threat Intelligence sources. Our work uses Neural Networks to perform the task of attribution and show that our method makes the attribution more accurate than other techniques and state-of-the-art methods.
Liu, Shuyong, Jiang, Hongrui, Li, Sizhao, Yang, Yang, Shen, Linshan.  2020.  A Feature Compression Technique for Anomaly Detection Using Convolutional Neural Networks. 2020 IEEE 14th International Conference on Anti-counterfeiting, Security, and Identification (ASID). :39–42.
Anomaly detection classification technology based on deep learning is one of the crucial technologies supporting network security. However, as the data increasing, this traditional model cannot guarantee that the false alarm rate is minimized while meeting the high detection rate. Additionally, distribution of imbalanced abnormal samples will lead to an increase in the error rate of the classification results. In this work, since CNN is effective in network intrusion classification, we embed a compressed feature layer in CNN (Convolutional Neural Networks). The purpose is to improve the efficiency of network intrusion detection. After our model was trained for 55 epochs and we set the learning rate of the model to 0.01, the detection rate reaches over 98%.
Li, Yizhi.  2020.  Research on Application of Convolutional Neural Network in Intrusion Detection. 2020 7th International Forum on Electrical Engineering and Automation (IFEEA). :720–723.
At present, our life is almost inseparable from the network, the network provides a lot of convenience for our life. However, a variety of network security incidents occur very frequently. In recent years, with the continuous development of neural network technology, more and more researchers have applied neural network to intrusion detection, which has developed into a new research direction in intrusion detection. As long as the neural network is provided with input data including network data packets, through the process of self-learning, the neural network can separate abnormal data features and effectively detect abnormal data. Therefore, the article innovatively proposes an intrusion detection method based on deep convolutional neural networks (CNN), which is used to test on public data sets. The results show that the model has a higher accuracy rate and a lower false negative rate than traditional intrusion detection methods.
2021-05-05
Hasan, Tooba, Adnan, Akhunzada, Giannetsos, Thanassis, Malik, Jahanzaib.  2020.  Orchestrating SDN Control Plane towards Enhanced IoT Security. 2020 6th IEEE Conference on Network Softwarization (NetSoft). :457—464.

The Internet of Things (IoT) is rapidly evolving, while introducing several new challenges regarding security, resilience and operational assurance. In the face of an increasing attack landscape, it is necessary to cater for the provision of efficient mechanisms to collectively detect sophisticated malware resulting in undesirable (run-time) device and network modifications. This is not an easy task considering the dynamic and heterogeneous nature of IoT environments; i.e., different operating systems, varied connected networks and a wide gamut of underlying protocols and devices. Malicious IoT nodes or gateways can potentially lead to the compromise of the whole IoT network infrastructure. On the other hand, the SDN control plane has the capability to be orchestrated towards providing enhanced security services to all layers of the IoT networking stack. In this paper, we propose an SDN-enabled control plane based orchestration that leverages emerging Long Short-Term Memory (LSTM) classification models; a Deep Learning (DL) based architecture to combat malicious IoT nodes. It is a first step towards a new line of security mechanisms that enables the provision of scalable AI-based intrusion detection focusing on the operational assurance of only those specific, critical infrastructure components,thus, allowing for a much more efficient security solution. The proposed mechanism has been evaluated with current state of the art datasets (i.e., N\_BaIoT 2018) using standard performance evaluation metrics. Our preliminary results show an outstanding detection accuracy (i.e., 99.9%) which significantly outperforms state-of-the-art approaches. Based on our findings, we posit open issues and challenges, and discuss possible ways to address them, so that security does not hinder the deployment of intelligent IoT-based computing systems.

2021-05-03
Paulsen, Brandon, Wang, Jingbo, Wang, Jiawei, Wang, Chao.  2020.  NEURODIFF: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation. 2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE). :784–796.
As neural networks make their way into safety-critical systems, where misbehavior can lead to catastrophes, there is a growing interest in certifying the equivalence of two structurally similar neural networks - a problem known as differential verification. For example, compression techniques are often used in practice for deploying trained neural networks on computationally- and energy-constrained devices, which raises the question of how faithfully the compressed network mimics the original network. Unfortunately, existing methods either focus on verifying a single network or rely on loose approximations to prove the equivalence of two networks. Due to overly conservative approximation, differential verification lacks scalability in terms of both accuracy and computational cost. To overcome these problems, we propose NEURODIFF, a symbolic and fine-grained approximation technique that drastically increases the accuracy of differential verification on feed-forward ReLU networks while achieving many orders-of-magnitude speedup. NEURODIFF has two key contributions. The first one is new convex approximations that more accurately bound the difference of two networks under all possible inputs. The second one is judicious use of symbolic variables to represent neurons whose difference bounds have accumulated significant error. We find that these two techniques are complementary, i.e., when combined, the benefit is greater than the sum of their individual benefits. We have evaluated NEURODIFF on a variety of differential verification tasks. Our results show that NEURODIFF is up to 1000X faster and 5X more accurate than the state-of-the-art tool.
2021-04-27
Sekar, K., Devi, K. Suganya, Srinivasan, P., SenthilKumar, V. M..  2020.  Deep Wavelet Architecture for Compressive sensing Recovery. 2020 Seventh International Conference on Information Technology Trends (ITT). :185–189.
The deep learning-based compressive Sensing (CS) has shown substantial improved performance and in run-time reduction with signal sampling and reconstruction. In most cases, moreover, these techniques suffer from disrupting artefacts or high-frequency contents at low sampling ratios. Similarly, this occurs in the multi-resolution sampling method, which further collects more components with lower frequencies. A promising innovation combining CS with convolutionary neural network has eliminated the sparsity constraint yet recovery persists slow. We propose a Deep wavelet based compressive sensing with multi-resolution framework provides better improvement in reconstruction as well as run time. The proposed model demonstrates outstanding quality on test functions over previous approaches.
2021-04-09
Lin, T., Shi, Y., Shu, N., Cheng, D., Hong, X., Song, J., Gwee, B. H..  2020.  Deep Learning-Based Image Analysis Framework for Hardware Assurance of Digital Integrated Circuits. 2020 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA). :1—6.
We propose an Artificial Intelligence (AI)/Deep Learning (DL)-based image analysis framework for hardware assurance of digital integrated circuits (ICs). Our aim is to examine and verify various hardware information from analyzing the Scanning Electron Microscope (SEM) images of an IC. In our proposed framework, we apply DL-based methods at all essential steps of the analysis. To the best of our knowledge, this is the first such framework that makes heavy use of DL-based methods at all essential analysis steps. Further, to reduce time and effort required in model re-training, we propose and demonstrate various automated or semi-automated training data preparation methods and demonstrate the effectiveness of using synthetic data to train a model. By applying our proposed framework to analyzing a set of SEM images of a large digital IC, we prove its efficacy. Our DL-based methods are fast, accurate, robust against noise, and can automate tasks that were previously performed mainly manually. Overall, we show that DL-based methods can largely increase the level of automation in hardware assurance of digital ICs and improve its accuracy.
2021-04-08
Zhang, J., Liao, Y., Zhu, X., Wang, H., Ding, J..  2020.  A Deep Learning Approach in the Discrete Cosine Transform Domain to Median Filtering Forensics. IEEE Signal Processing Letters. 27:276—280.
This letter presents a novel median filtering forensics approach, based on a convolutional neural network (CNN) with an adaptive filtering layer (AFL), which is built in the discrete cosine transform (DCT) domain. Using the proposed AFL, the CNN can determine the main frequency range closely related with the operational traces. Then, to automatically learn the multi-scale manipulation features, a multi-scale convolutional block is developed, exploring a new multi-scale feature fusion strategy based on the maxout function. The resultant features are further processed by a convolutional stream with pooling and batch normalization operations, and finally fed into the classification layer with the Softmax function. Experimental results show that our proposed approach is able to accurately detect the median filtering manipulation and outperforms the state-of-the-art schemes, especially in the scenarios of low image resolution and serious compression loss.
Mayer, O., Stamm, M. C..  2020.  Forensic Similarity for Digital Images. IEEE Transactions on Information Forensics and Security. 15:1331—1346.
In this paper, we introduce a new digital image forensics approach called forensic similarity, which determines whether two image patches contain the same forensic trace or different forensic traces. One benefit of this approach is that prior knowledge, e.g., training samples, of a forensic trace is not required to make a forensic similarity decision on it in the future. To do this, we propose a two-part deep-learning system composed of a convolutional neural network-based feature extractor and a three-layer neural network, called the similarity network. This system maps the pairs of image patches to a score indicating whether they contain the same or different forensic traces. We evaluated the system accuracy of determining whether two image patches were captured by the same or different camera model and manipulated by the same or a different editing operation and the same or a different manipulation parameter, given a particular editing operation. Experiments demonstrate applicability to a variety of forensic traces and importantly show efficacy on “unknown” forensic traces that were not used to train the system. Experiments also show that the proposed system significantly improves upon prior art, reducing error rates by more than half. Furthermore, we demonstrated the utility of the forensic similarity approach in two practical applications: forgery detection and localization, and database consistency verification.
Rhee, K. H..  2020.  Composition of Visual Feature Vector Pattern for Deep Learning in Image Forensics. IEEE Access. 8:188970—188980.

In image forensics, to determine whether the image is impurely transformed, it extracts and examines the features included in the suspicious image. In general, the features extracted for the detection of forgery images are based on numerical values, so it is somewhat unreasonable to use in the CNN structure for image classification. In this paper, the extraction method of a feature vector is using a least-squares solution. Treat a suspicious image like a matrix and its solution to be coefficients as the feature vector. Get two solutions from two images of the original and its median filter residual (MFR). Subsequently, the two features were formed into a visualized pattern and then fed into CNN deep learning to classify the various transformed images. A new structure of the CNN net layer was also designed by hybrid with the inception module and the residual block to classify visualized feature vector patterns. The performance of the proposed image forensics detection (IFD) scheme was measured with the seven transformed types of image: average filtered (window size: 3 × 3), gaussian filtered (window size: 3 × 3), JPEG compressed (quality factor: 90, 70), median filtered (window size: 3 × 3, 5 × 5), and unaltered. The visualized patterns are fed into the image input layer of the designed CNN hybrid model. Throughout the experiment, the accuracy of median filtering detection was 98% over. Also, the area under the curve (AUC) by sensitivity (TP: true positive rate) and 1-specificity (FP: false positive rate) results of the proposed IFD scheme approached to `1' on the designed CNN hybrid model. Experimental results show high efficiency and performance to classify the various transformed images. Therefore, the grade evaluation of the proposed scheme is “Excellent (A)”.