Visible to the public Biblio

Filters: Keyword is noise reduction  [Clear All Filters]
Hashemi, M. J., Keller, E..  2020.  Enhancing Robustness Against Adversarial Examples in Network Intrusion Detection Systems. 2020 IEEE Conference on Network Function Virtualization and Software Defined Networks (NFV-SDN). :37—43.

The increase of cyber attacks in both the numbers and varieties in recent years demands to build a more sophisticated network intrusion detection system (NIDS). These NIDS perform better when they can monitor all the traffic traversing through the network like when being deployed on a Software-Defined Network (SDN). Because of the inability to detect zero-day attacks, signature-based NIDS which were traditionally used for detecting malicious traffic are beginning to get replaced by anomaly-based NIDS built on neural networks. However, recently it has been shown that such NIDS have their own drawback namely being vulnerable to the adversarial example attack. Moreover, they were mostly evaluated on the old datasets which don't represent the variety of attacks network systems might face these days. In this paper, we present Reconstruction from Partial Observation (RePO) as a new mechanism to build an NIDS with the help of denoising autoencoders capable of detecting different types of network attacks in a low false alert setting with an enhanced robustness against adversarial example attack. Our evaluation conducted on a dataset with a variety of network attacks shows denoising autoencoders can improve detection of malicious traffic by up to 29% in a normal setting and by up to 45% in an adversarial setting compared to other recently proposed anomaly detectors.

Chow, Ka-Ho, Wei, Wenqi, Wu, Yanzhao, Liu, Ling.  2019.  Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks. 2019 IEEE International Conference on Big Data (Big Data). :1282–1291.
Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. In this paper, we present MODEF, a cross-layer model diversity ensemble framework. MODEF intelligently combines unsupervised model denoising ensemble with supervised model verification ensemble by quantifying model diversity, aiming to boost the robustness of the target model against adversarial examples. Evaluated using eleven representative attacks on popular benchmark datasets, we show that MODEF achieves remarkable defense success rates, compared with existing defense methods, and provides a superior capability of repairing adversarial inputs and making correct predictions with high accuracy in the presence of black-box attacks.
Karaküçük, Ahmet, Dirik, A. Emir.  2019.  Source Device Attribution of Thermal Images Captured with Handheld IR Cameras. 2019 11th International Conference on Electrical and Electronics Engineering (ELECO). :547—551.

Source camera attribution of digital images has been a hot research topic in digital forensics literature. However, the thermal cameras and the radiometric data they generate stood as a nascent topic, as such devices are expensive and tailored for specific use-cases - not adapted by the masses. This has changed dramatically, with the low-cost, pluggable thermal-camera add-ons to smartphones and similar low-cost pocket-size thermal cameras introduced to consumers recently, which enabled the use of thermal imaging devices for the masses. In this paper, we are going to investigate the use of an established source device attribution method on radiometric data produced with a consumer-level, low-cost handheld thermal camera. The results we represent in this paper are promising and show that it is quite possible to attribute thermal images with their source camera.

Jiang, H., Turki, T., Wang, J. T. L..  2018.  DLGraph: Malware Detection Using Deep Learning and Graph Embedding. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). :1029-1033.

In this paper we present a new approach, named DLGraph, for malware detection using deep learning and graph embedding. DLGraph employs two stacked denoising autoencoders (SDAs) for representation learning, taking into consideration computer programs' function-call graphs and Windows application programming interface (API) calls. Given a program, we first use a graph embedding technique that maps the program's function-call graph to a vector in a low-dimensional feature space. One SDA in our deep learning model is used to learn a latent representation of the embedded vector of the function-call graph. The other SDA in our model is used to learn a latent representation of the given program's Windows API calls. The two learned latent representations are then merged to form a combined feature vector. Finally, we use softmax regression to classify the combined feature vector for predicting whether the given program is malware or not. Experimental results based on different datasets demonstrate the effectiveness of the proposed approach and its superiority over a related method.

Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., Zhu, J..  2018.  Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. :1778–1787.
Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose high-level representation guided denoiser (HGD) as a defense for image classification. Standard denoiser suffers from the error amplification effect, in which small residual adversarial noise is progressively amplified and leads to wrong classifications. HGD overcomes this problem by using a loss function defined as the difference between the target model's outputs activated by the clean image and denoised image. Compared with ensemble adversarial training which is the state-of-the-art defending method on large images, HGD has three advantages. First, with HGD as a defense, the target model is more robust to either white-box or black-box adversarial attacks. Second, HGD can be trained on a small subset of the images and generalizes well to other images and unseen classes. Third, HGD can be transferred to defend models other than the one guiding it. In NIPS competition on defense against adversarial attacks, our HGD solution won the first place and outperformed other models by a large margin.1
Aygun, R. C., Yavuz, A. G..  2017.  Network Anomaly Detection with Stochastically Improved Autoencoder Based Models. 2017 IEEE 4th International Conference on Cyber Security and Cloud Computing (CSCloud). :193–198.

Intrusion detection systems do not perform well when it comes to detecting zero-day attacks, therefore improving their performance in that regard is an active research topic. In this study, to detect zero-day attacks with high accuracy, we proposed two deep learning based anomaly detection models using autoencoder and denoising autoencoder respectively. The key factor that directly affects the accuracy of the proposed models is the threshold value which was determined using a stochastic approach rather than the approaches available in the current literature. The proposed models were tested using the KDDTest+ dataset contained in NSL-KDD, and we achieved an accuracy of 88.28% and 88.65% respectively. The obtained results show that, as a singular model, our proposed anomaly detection models outperform any other singular anomaly detection methods and they perform almost the same as the newly suggested hybrid anomaly detection models.

Kogos, K. G., Filippova, K. S., Epishkina, A. V..  2017.  Fully homomorphic encryption schemes: The state of the art. 2017 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus). :463–466.

The challenge of maintaining confidentiality of stored and processed data in a remote database or cloud is quite urgent. Using homomorphic encryption may solve the problem, because it allows to compute some functions over encrypted data without preliminary deciphering of data. Fully homomorphic encryption schemes have a number of limitations such as accumulation of noise and increase of ciphertext extension during performing operations, the range of operations is limited. Nowadays a lot of homomorphic encryption schemes and their modifications have been investigated, so more than 25 reports on homomorphic encryption schemes have already been published on Cryptology ePrint Archive for 2016. We propose an overview of current Fully Homomorphic Encryption Schemes and analyze specific operations for databases which homomorphic cryptosystems allow to perform. We also investigate the possibility of sorting over encrypted data and present our approach to compare data encrypted by Multi-bit FHE scheme.

Saurabh, A., Kumar, A., Anitha, U..  2015.  Performance analysis of various wavelet thresholding techniques for despeckiling of sonar images. 2015 3rd International Conference on Signal Processing, Communication and Networking (ICSCN). :1–7.

Image Denoising nowadays is a great Challenge in the field of image processing. Since Discrete wavelet transform (DWT) is one of the powerful and perspective approaches in the area of image de noising. But fixing an optimal threshold is the key factor to determine the performance of denoising algorithm using (DWT). The optimal threshold can be estimated from the image statistics for getting better performance of denoising in terms of clarity or quality of the images. In this paper we analyzed various methods of denoising from the sonar image by using various thresholding methods (Vishnu Shrink, Bayes Shrink and Neigh Shrink) experimentally and compare the result in terms of various image quality parameters. (PSNR,MSE,SSIM and Entropy). The results of the proposed method show that there is an improvenment in the visual quality of sonar images by suppressing the speckle noise and retaining edge details.

Rubel, O., Ponomarenko, N., Lukin, V., Astola, J., Egiazarian, K..  2015.  HVS-based local analysis of denoising efficiency for DCT-based filters. 2015 Second International Scientific-Practical Conference Problems of Infocommunications Science and Technology (PIC S T). :189–192.

Images acquired and processed in communication and multimedia systems are often noisy. Thus, pre-filtering is a typical stage to remove noise. At this stage, a special attention has to be paid to image visual quality. This paper analyzes denoising efficiency from the viewpoint of visual quality improvement using metrics that take into account human vision system (HVS). Specific features of the paper consist in, first, considering filters based on discrete cosine transform (DCT) and, second, analyzing the filter performance locally. Such an analysis is possible due to the structure and peculiarities of the metric PSNR-HVS-M. It is shown that a more advanced DCT-based filter BM3D outperforms a simpler (and faster) conventional DCT-based filter in locally active regions, i.e., neighborhoods of edges and small-sized objects. This conclusions allows accelerating BM3D filter and can be used in further improvement of the analyzed denoising techniques.

Pohjalainen, Jouni, Fabien Ringeval, Fabien, Zhang, Zixing, Schuller, Björn.  2016.  Spectral and Cepstral Audio Noise Reduction Techniques in Speech Emotion Recognition. Proceedings of the 2016 ACM on Multimedia Conference. :670–674.

Signal noise reduction can improve the performance of machine learning systems dealing with time signals such as audio. Real-life applicability of these recognition technologies requires the system to uphold its performance level in variable, challenging conditions such as noisy environments. In this contribution, we investigate audio signal denoising methods in cepstral and log-spectral domains and compare them with common implementations of standard techniques. The different approaches are first compared generally using averaged acoustic distance metrics. They are then applied to automatic recognition of spontaneous and natural emotions under simulated smartphone-recorded noisy conditions. Emotion recognition is implemented as support vector regression for continuous-valued prediction of arousal and valence on a realistic multimodal database. In the experiments, the proposed methods are found to generally outperform standard noise reduction algorithms.

A. Roy, S. P. Maity.  2015.  "On segmentation of CS reconstructed MR images". 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR). :1-6.

This paper addresses the issue of magnetic resonance (MR) Image reconstruction at compressive sampling (or compressed sensing) paradigm followed by its segmentation. To improve image reconstruction problem at low measurement space, weighted linear prediction and random noise injection at unobserved space are done first, followed by spatial domain de-noising through adaptive recursive filtering. Reconstructed image, however, suffers from imprecise and/or missing edges, boundaries, lines, curvatures etc. and residual noise. Curvelet transform is purposely used for removal of noise and edge enhancement through hard thresholding and suppression of approximate sub-bands, respectively. Finally Genetic algorithms (GAs) based clustering is done for segmentation of sharpen MR Image using weighted contribution of variance and entropy values. Extensive simulation results are shown to highlight performance improvement of both image reconstruction and segmentation problems.

Shimauchi, S., Ohmuro, H..  2014.  Accurate adaptive filtering in square-root Hann windowed short-time fourier transform domain. Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on. :1305-1309.

A novel short-time Fourier transform (STFT) domain adaptive filtering scheme is proposed that can be easily combined with nonlinear post filters such as residual echo or noise reduction in acoustic echo cancellation. Unlike normal STFT subband adaptive filters, which suffers from aliasing artifacts due to its poor prototype filter, our scheme achieves good accuracy by exploiting the relationship between the linear convolution and the poor prototype filter, i.e., the STFT window function. The effectiveness of our scheme was confirmed through the results of simulations conducted to compare it with conventional methods.

Bin Sun, Shutao Li, Jun Sun.  2014.  Scanned Image Descreening With Image Redundancy and Adaptive Filtering. Image Processing, IEEE Transactions on. 23:3698-3710.

Currently, most electrophotographic printers use halftoning technique to print continuous tone images, so scanned images obtained from such hard copies are usually corrupted by screen like artifacts. In this paper, a new model of scanned halftone image is proposed to consider both printing distortions and halftone patterns. Based on this model, an adaptive filtering based descreening method is proposed to recover high quality contone images from the scanned images. Image redundancy based denoising algorithm is first adopted to reduce printing noise and attenuate distortions. Then, screen frequency of the scanned image and local gradient features are used for adaptive filtering. Basic contone estimate is obtained by filtering the denoised scanned image with an anisotropic Gaussian kernel, whose parameters are automatically adjusted with the screen frequency and local gradient information. Finally, an edge-preserving filter is used to further enhance the sharpness of edges to recover a high quality contone image. Experiments on real scanned images demonstrate that the proposed method can recover high quality contone images from the scanned images. Compared with the state-of-the-art methods, the proposed method produces very sharp edges and much cleaner smooth regions.

Jian Wang, Lin Mei, Yi Li, Jian-Ye Li, Kun Zhao, Yuan Yao.  2014.  Variable Window for Outlier Detection and Impulsive Noise Recognition in Range Images. Cluster, Cloud and Grid Computing (CCGrid), 2014 14th IEEE/ACM International Symposium on. :857-864.

To improve comprehensive performance of denoising range images, an impulsive noise (IN) denoising method with variable windows is proposed in this paper. Founded on several discriminant criteria, the principles of dropout IN detection and outlier IN detection are provided. Subsequently, a nearest non-IN neighbors searching process and an Index Distance Weighted Mean filter is combined for IN denoising. As key factors of adapatablity of the proposed denoising method, the sizes of two windows for outlier INs detection and INs denoising are investigated. Originated from a theoretical model of invader occlusion, variable window is presented for adapting window size to dynamic environment of each point, accompanying with practical criteria of adaptive variable window size determination. Experiments on real range images of multi-line surface are proceeded with evaluations in terms of computational complexity and quality assessment with comparison analysis among a few other popular methods. It is indicated that the proposed method can detect the impulsive noises with high accuracy, meanwhile, denoise them with strong adaptability with the help of variable window.

Jialing Mo, Qiang He, Weiping Hu.  2014.  An adaptive threshold de-noising method based on EEMD. Signal Processing, Communications and Computing (ICSPCC), 2014 IEEE International Conference on. :209-214.

In view of the difficulty in selecting wavelet base and decomposition level for wavelet-based de-noising method, this paper proposes an adaptive de-noising method based on Ensemble Empirical Mode Decomposition (EEMD). The autocorrelation, cross-correlation method is used to adaptively find the signal-to-noise boundary layer of the EEMD in this method. Then the noise dominant layer is filtered directly and the signal dominant layer is threshold de-noised. Finally, the de-noising signal is reconstructed by each layer component which is de-noised. This method solves the problem of mode mixing in Empirical Mode Decomposition (EMD) by using EEMD and combines the advantage of wavelet threshold. In this paper, we focus on the analysis and verification of the correctness of the adaptive determination of the noise dominant layer. The simulation experiment results prove that this de-noising method is efficient and has good adaptability.

Zurek, E.E., Gamarra, A.M.R., Escorcia, G.J.R., Gutierrez, C., Bayona, H., Perez, R., Garcia, X..  2014.  Spectral analysis techniques for acoustic fingerprints recognition. Image, Signal Processing and Artificial Vision (STSIVA), 2014 XIX Symposium on. :1-5.

This article presents results of the recognition process of acoustic fingerprints from a noise source using spectral characteristics of the signal. Principal Components Analysis (PCA) is applied to reduce the dimensionality of extracted features and then a classifier is implemented using the method of the k-nearest neighbors (KNN) to identify the pattern of the audio signal. This classifier is compared with an Artificial Neural Network (ANN) implementation. It is necessary to implement a filtering system to the acquired signals for 60Hz noise reduction generated by imperfections in the acquisition system. The methods described in this paper were used for vessel recognition.