# Biblio

In this paper, RBF-based multistage auto-encoders are used to detect IDS attacks. RBF has numerous applications in various actual life settings. The planned technique involves a two-part multistage auto-encoder and RBF. The multistage auto-encoder is applied to select top and sensitive features from input data. The selected features from the multistage auto-encoder is wired as input to the RBF and the RBF is trained to categorize the input data into two labels: attack or no attack. The experiment was realized using MATLAB2018 on a dataset comprising 175,341 case, each of which involves 42 features and is authenticated using 82,332 case. The developed approach here has been applied for the first time, to the knowledge of the authors, to detect IDS attacks with 98.80% accuracy when validated using UNSW-NB15 dataset. The experimental results show the proposed method presents satisfactory results when compared with those obtained in this field.

Web applications are a frequent target of successful attacks. In most web frameworks, the damage is amplified by the fact that application code is responsible for security enforcement. In this paper, we design and evaluate Radiatus, a shared-nothing web framework where application-specific computation and storage on the server is contained within a sandbox with the privileges of the end-user. By strongly isolating users, user data and service availability can be protected from application vulnerabilities. To make Radiatus practical at the scale of modern web applications, we introduce a distributed capabilities system to allow fine-grained secure resource sharing across the many distributed services that compose an application. We analyze the strengths and weaknesses of a shared-nothing web architecture, which protects applications from a large class of vulnerabilities, but adds an overhead of 60.7% per server and requires an additional 31MB of memory per active user. We demonstrate that the system can scale to 20K operations per second on a 500-node AWS cluster.

As modern attacks become more stealthy and persistent, detecting or preventing them at their early stages becomes virtually impossible. Instead, an attack investigation or provenance system aims to continuously monitor and log interesting system events with minimal overhead. Later, if the system observes any anomalous behavior, it analyzes the log to identify who initiated the attack and which resources were affected by the attack and then assess and recover from any damage incurred. However, because of a fundamental tradeoff between log granularity and system performance, existing systems typically record system-call events without detailed program-level activities (e.g., memory operation) required for accurately reconstructing attack causality or demand that every monitored program be instrumented to provide program-level information. To address this issue, we propose RAIN, a Refinable Attack INvestigation system based on a record-replay technology that records system-call events during runtime and performs instruction-level dynamic information flow tracking (DIFT) during on-demand process replay. Instead of replaying every process with DIFT, RAIN conducts system-call-level reachability analysis to filter out unrelated processes and to minimize the number of processes to be replayed, making inter-process DIFT feasible. Evaluation results show that RAIN effectively prunes out unrelated processes and determines attack causality with negligible false positive rates. In addition, the runtime overhead of RAIN is similar to existing system-call level provenance systems and its analysis overhead is much smaller than full-system DIFT.

This paper focuses on one type of Covert Storage Channel (CSC) that uses the 6-bit TCP flag header in TCP/IP network packets to transmit secret messages between accomplices. We use relative entropy to characterize the irregularity of network flows in comparison to normal traffic. A normal profile is created by the frequency distribution of TCP flags in regular traffic packets. In detection, the TCP flag frequency distribution of network traffic is computed for each unique IP pair. In order to evaluate the accuracy and efficiency of the proposed method, this study uses real regular traffic data sets as well as CSC messages using coding schemes under assumptions of both clear text, composed by a list of keywords common in Unix systems, and encrypted text. Moreover, smart accomplices may use only those TCP flags that are ever appearing in normal traffic. Then, in detection, the relative entropy can reveal the dissimilarity of a different frequency distribution from this normal profile. We have also used different data processing methods in detection: one method summarizes all the packets for a pair of IP addresses into one flow and the other uses a sliding moving window over such a flow to generate multiple frames of packets. The experimentation results, displayed by Receiver Operating Characteristic (ROC) curves, have shown that the method is promising to differentiate normal and CSC traffic packet streams. Furthermore the delay of raising an alert is analyzed for CSC messages to show its efficiency.

Let G be a finite connected graph, and let ρ be the spectral radius of its universal cover. For example, if G is k-regular then ρ=2√k−1. We show that for every r, there is an r-covering (a.k.a. an r-lift) of G where all the new eigenvalues are bounded from above by ρ. It follows that a bipartite Ramanujan graph has a Ramanujan r-covering for every r. This generalizes the r=2 case due to Marcus, Spielman and Srivastava (2013). Every r-covering of G corresponds to a labeling of the edges of G by elements of the symmetric group Sr. We generalize this notion to labeling the edges by elements of various groups and present a broader scenario where Ramanujan coverings are guaranteed to exist. In particular, this shows the existence of richer families of bipartite Ramanujan graphs than was known before. Inspired by Marcus-Spielman-Srivastava, a crucial component of our proof is the existence of interlacing families of polynomials for complex reflection groups. The core argument of this component is taken from Marcus-Spielman-Srivastava (2015). Another important ingredient of our proof is a new generalization of the matching polynomial of a graph. We define the r-th matching polynomial of G to be the average matching polynomial of all r-coverings of G. We show this polynomial shares many properties with the original matching polynomial. For example, it is real rooted with all its roots inside [−ρ,ρ].

We present RamCrypt, a solution that allows unmodified Linux processes to transparently work on encrypted data. RamCrypt can be deployed and enabled on a per-process basis without recompiling user-mode applications. In every enabled process, data is only stored in cleartext for the moment it is processed, and otherwise stays encrypted in RAM. In particular, the required encryption keys do not reside in RAM, but are stored in CPU registers only. Hence, RamCrypt effectively thwarts memory disclosure attacks, which grant unauthorized access to process memory, as well as physical attacks such as cold boot and DMA attacks. In its default configuration, RamCrypt exposes only up to 4 memory pages in cleartext at the same time. For the nginx web server serving encrypted HTTPS pages under heavy load, the necessary TLS secret key is hidden for 97% of its time.

Trying to solve the risk of data privacy disclosure in classification process, a Random Forest algorithm under differential privacy named DPRF-gini is proposed in the paper. In the process of building decision tree, the algorithm first disturbed the process of feature selection and attribute partition by using exponential mechanism, and then meet the requirement of differential privacy by adding Laplace noise to the leaf node. Compared with the original algorithm, Empirical results show that protection of data privacy is further enhanced while the accuracy of the algorithm is slightly reduced.

Phishing is a major concern on the Internet today and many users are falling victim because of criminal's deceitful tactics. Blacklisting is still the most common defence users have against such phishing websites, but is failing to cope with the increasing number. In recent years, researchers have devised modern ways of detecting such websites using machine learning. One such method is to create machine learnt models of URL features to classify whether URLs are phishing. However, there are varying opinions on what the best approach is for features and algorithms. In this paper, the objective is to evaluate the performance of the Random Forest algorithm using a lexical only dataset. The performance is benchmarked against other machine learning algorithms and additionally against those reported in the literature. Initial results from experiments indicate that the Random Forest algorithm performs the best yielding an 86.9% accuracy.

Moving target defense (MTD) is a proactive defense mechanism of changing the attack surface to increase an attacker's confusion and/or uncertainty, which invalidates its intelligence gained through reconnaissance and/or network scanning attacks. In this work, we propose software-defined networking (SDN)-based MTD technique using the shuffling of IP addresses and port numbers aiming to obfuscate both network and transport layers' real identities of the host and the service for defending against the network reconnaissance and scanning attacks. We call our proposed MTD technique Random Host and Service Multiplexing, namely RHSM. RHSM allows each host to use random, multiple virtual IP addresses to be dynamically and periodically shuffled. In addition, it uses short-lived, multiple virtual port numbers for an active service running on the host. Our proposed RHSM is novel in that we employ multiplexing (or de-multiplexing) to dynamically change and remap from all the virtual IPs of the host to the real IP or the virtual ports of the services to the real port, respectively. Via extensive simulation experiments, we prove how effectively and efficiently RHSM outperforms a baseline counterpart (i.e., a static network without RHSM) in terms of the attack success probability and defense cost.

Vector space models (VSMs) are mathematically well-defined frameworks that have been widely used in text processing. In these models, high-dimensional, often sparse vectors represent text units. In an application, the similarity of vectors -- and hence the text units that they represent -- is computed by a distance formula. The high dimensionality of vectors, however, is a barrier to the performance of methods that employ VSMs. Consequently, a dimensionality reduction technique is employed to alleviate this problem. This paper introduces a new method, called Random Manhattan Indexing (RMI), for the construction of L1 normed VSMs at reduced dimensionality. RMI combines the construction of a VSM and dimension reduction into an incremental, and thus scalable, procedure. In order to attain its goal, RMI employs the sparse Cauchy random projections.

Strength of security and privacy of any cryptographic mechanisms that use random numbers require that the random numbers generated have two important properties namely 1. Uniform distribution and 2. Independence. With the growth of Internet many devices are connected to Internet that host sensors. One idea proposed is to use sensor data as seed for Random Number Generator (RNG) since sensors measure the physical phenomena that exhibit randomness over time. The random numbers generated from sensor data can be used for cryptographic algorithms in Internet activities. These sensor data also pose weaknesses where sensors may be under adversarial control that may lead to generating expected random sequence which breaks the security and privacy. This paper proposes a wash-rinse-spin approach to process the raw sensor data that increases randomness in the seed value. The generated sequences from two sensors are combined by Decimation method to improve unpredictability. This makes the sensor data to be more secure in generating random numbers preventing attackers from knowing the random sequence through adversarial control.

In this paper a random number generation method based on a piecewise linear one dimensional (PL1D) discrete time chaotic maps is proposed for applications in cryptography and steganography. Appropriate parameters are determined by examining the distribution of underlying chaotic signal and random number generator (RNG) is numerically verified by four fundamental statistical test of FIPS 140-2. Proposed design is practically realized on the field programmable analog and digital arrays (FPAA-FPGA). Finally it is experimentally verified that the presented RNG fulfills the NIST 800-22 randomness test without post processing.

Wireless sensor networks are responsible for sensing, gathering and processing the information of the objects in the network coverage area. Basic data fusion technology generally does not provide data privacy protection mechanism, and the privacy protection mechanism in health care, military reconnaissance, smart home and other areas of the application is usually indispensable. In this paper, we consider the privacy, confidentiality, and the accuracy of fusion results, and propose a data fusion algorithm for privacy preserving. This algorithm relies on the characteristics of data fusion, and uses the method of pre-distribution random number in the node to get the privacy protection requirements of the original data. Theoretical analysis shows that the malicious attacker attempts to steal the difficulty of node privacy in PPND algorithm. At the same time in the TOSSIM simulation results also show that, compared with TAG, SMART algorithm, PPND algorithm in the data traffic, the convergence accuracy of the good performance.

We study the problem of approximate nearest neighbor search in \$d\$-dimensional Hamming space \0,1\d. We study the complexity of the problem in the famous cell-probe model, a classic model for data structures. We consider algorithms in the cell-probe model with limited adaptivity, where the algorithm makes k rounds of parallel accesses to the data structure for a given k. For any k ≥ 1, we give a simple randomized algorithm solving the approximate nearest neighbor search using k rounds of parallel memory accesses, with O(k(log d)1/k) accesses in total. We also give a more sophisticated randomized algorithm using O(k+(1/k log d)O(1/k)) memory accesses in k rounds for large enough k. Both algorithms use data structures of size polynomial in n, the number of points in the database. We prove an Ω(1/k(log d)1/k) lower bound for the total number of memory accesses required by any randomized algorithm solving the approximate nearest neighbor search within k ≤ (log log d)/(2 log log log d) rounds of parallel memory accesses on any data structures of polynomial size. This lower bound shows that our first algorithm is asymptotically optimal for any constant round k. And our second algorithm approaches the asymptotically optimal tradeoff between rounds and memory accesses, in a sense that the lower bound of memory accesses for any k1 rounds can be matched by the algorithm within k2=O(k1) rounds. In the extreme, for some large enough k=Θ((log log d)/(log log log d)), our second algorithm matches the Θ((log log d)/(log log log d)) tight bound for fully adaptive algorithms for approximate nearest neighbor search due to Chakrabarti and Regev.