Biblio

Language vector space models (VSMs) have recently proven to be effective across a variety of tasks. In VSMs, each word in a corpus is represented as a real-valued vector. These vectors can be used as features in many applications in machine learning and natural language processing. In this paper, we study the effect of vector space representations in cyber security. In particular, we consider a passive traffic analysis attack (Website Fingerprinting) that threatens users' navigation privacy on the web. By using anonymous communication, Internet users (such as online activists) may wish to hide the destination of web pages they access for different reasons such as avoiding tyrant governments. Traditional website fingerprinting studies collect packets from the users' network and extract features that are used by machine learning techniques to reveal the destination of certain web pages. In this work, we propose the packet to vector (P2V) approach where we model website fingerprinting attack using word vector representations. We show how the suggested model outperforms previous website fingerprinting works.

Language vector space models (VSMs) have recently proven to be effective across a variety of tasks. In VSMs, each word in a corpus is represented as a real-valued vector. These vectors can be used as features in many applications in machine learning and natural language processing. In this paper, we study the effect of vector space representations in cyber security. In particular, we consider a passive traffic analysis attack (Website Fingerprinting) that threatens users' navigation privacy on the web. By using anonymous communication, Internet users (such as online activists) may wish to hide the destination of web pages they access for different reasons such as avoiding tyrant governments. Traditional website fingerprinting studies collect packets from the users' network and extract features that are used by machine learning techniques to reveal the destination of certain web pages. In this work, we propose the packet to vector (P2V) approach where we model website fingerprinting attack using word vector representations. We show how the suggested model outperforms previous website fingerprinting works.

Segmentation of land and water regions is necessary in many applications involving analysis of remote sensing imagery. Not only is manual segmentation of these regions prone to considerable subjective variability, but the large volume of imagery collected by modern platforms makes manual segmentation extremely tedious to perform, particularly in applications that require frequent re-measurement. This paper examines a robust, semi-automated approach that utilizes simple and efficient machine learning algorithms to perform supervised classification of multi-spectral image data into land and water regions. By combining the four wavelength bands widely available in imaging platforms such as IKONOS, QuickBird, and GeoEye-1 with basic texture metrics, high quality segmentation can be achieved. An efficient workflow was created by constructing a Graphical User Interface (GUI) to these machine learning algorithms.

Most network traffic analysis applications are designed to discover malicious activity by only relying on high-level flow-based message properties. However, to detect security breaches that are specifically designed to target one network (e.g., Advanced Persistent Threats), deep packet inspection and anomaly detection are indispensible. In this paper, we focus on how we can support experts in discovering whether anomalies at message level imply a security risk at network level. In SNAPS (Semantic Network traffic Analysis through Projection and Selection), we provide a bottom-up pixel-oriented approach for network traffic analysis where the expert starts with low-level anomalies and iteratively gains insight in higher level events through the creation of multiple selections of interest in parallel. The tight integration between visualization and machine learning enables the expert to iteratively refine anomaly scores, making the approach suitable for both post-traffic analysis and online monitoring tasks. To illustrate the effectiveness of this approach, we present example explorations on two real-world data sets for the detection and understanding of potential Advanced Persistent Threats in progress.

What you see is not definitely believable is not a rare case in the cyber security monitoring. However, due to various tricks of camouflages, such as packing or virutal private network (VPN), detecting "advanced persistent threat"(APT) by only signature based malware detection system becomes more and more intractable. On the other hand, by carefully modeling users' subsequent behaviors of daily routines, probability for one account to generate certain operations can be estimated and used in anomaly detection. To the best of our knowledge so far, a novel behavioral analytic framework, which is dedicated to analyze Active Directory domain service logs and to monitor potential inside threat, is now first proposed in this project. Experiments on real dataset not only show that the proposed idea indeed explores a new feasible direction for cyber security monitoring, but also gives a guideline on how to deploy this framework to various environments.

In this article, we review previous work on biometric security under a recent framework proposed in the field of adversarial machine learning. This allows us to highlight novel insights on the security of biometric systems when operating in the presence of intelligent and adaptive attackers that manipulate data to compromise normal system operation. We show how this framework enables the categorization of known and novel vulnerabilities of biometric recognition systems, along with the corresponding attacks, countermeasures, and defense mechanisms. We report two application examples, respectively showing how to fabricate a more effective face spoofing attack, and how to counter an attack that exploits an unknown vulnerability of an adaptive face-recognition system to compromise its face templates.

Computing systems and networks become increasingly large and complex with a variety of compromises and vulnerabilities. The network security and privacy are of great concern today, where self-defense against different kinds of attacks in an autonomous and holistic manner is a challenging topic. To address this problem, we developed an innovative technology called Bionic Autonomic Nervous System (BANS). The BANS is analogous to biological nervous system, which consists of basic modules like cyber axon, cyber neuron, peripheral nerve and central nerve. We also presented an innovative self-defense mechanism which utilizes the Fuzzy Logic, Neural Networks, and Entropy Awareness, etc. Equipped with the BANS, computer and network systems can intelligently self-defend against both known and unknown compromises/attacks including denial of services (DoS), spyware, malware, and virus. BANS also enabled multiple computers to collaboratively fight against some distributed intelligent attacks like DDoS. We have implemented the BANS in practice. Some case studies and experimental results exhibited the effectiveness and efficiency of the BANS and the self-defense mechanism.

Interactive visualization provides valuable support for exploring, analyzing, and understanding textual documents. Certain tasks, however, require that insights derived from visual abstractions are verified by a human expert perusing the source text. So far, this problem is typically solved by offering overview-detail techniques, which present different views with different levels of abstractions. This often leads to problems with visual continuity. Focus-context techniques, on the other hand, succeed in accentuating interesting subsections of large text documents but are normally not suited for integrating visual abstractions. With VarifocalReader we present a technique that helps to solve some of these approaches' problems by combining characteristics from both. In particular, our method simplifies working with large and potentially complex text documents by simultaneously offering abstract representations of varying detail, based on the inherent structure of the document, and access to the text itself. In addition, VarifocalReader supports intra-document exploration through advanced navigation concepts and facilitates visual analysis tasks. The approach enables users to apply machine learning techniques and search mechanisms as well as to assess and adapt these techniques. This helps to extract entities, concepts and other artifacts from texts. In combination with the automatic generation of intermediate text levels through topic segmentation for thematic orientation, users can test hypotheses or develop interesting new research questions. To illustrate the advantages of our approach, we provide usage examples from literature studies.

Botnet detection represents one of the most crucial prerequisites of successful botnet neutralization. This paper explores how accurate and timely detection can be achieved by using supervised machine learning as the tool of inferring about malicious botnet traffic. In order to do so, the paper introduces a novel flow-based detection system that relies on supervised machine learning for identifying botnet network traffic. For use in the system we consider eight highly regarded machine learning algorithms, indicating the best performing one. Furthermore, the paper evaluates how much traffic needs to be observed per flow in order to capture the patterns of malicious traffic. The proposed system has been tested through the series of experiments using traffic traces originating from two well-known P2P botnets and diverse non-malicious applications. The results of experiments indicate that the system is able to accurately and timely detect botnet traffic using purely flow-based traffic analysis and supervised machine learning. Additionally, the results show that in order to achieve accurate detection traffic flows need to be monitored for only a limited time period and number of packets per flow. This indicates a strong potential of using the proposed approach within a future on-line detection framework.

This paper proposes and describes an active authentication model based on user profiles built from user-issued commands when interacting with GUI-based application. Previous behavioral models derived from user issued commands were limited to analyzing the user's interaction with the *Nix (Linux or Unix) command shell program. Human-computer interaction (HCI) research has explored the idea of building users profiles based on their behavioral patterns when interacting with such graphical interfaces. It did so by analyzing the user's keystroke and/or mouse dynamics. However, none had explored the idea of creating profiles by capturing users' usage characteristics when interacting with a specific application beyond how a user strikes the keyboard or moves the mouse across the screen. We obtain and utilize a dataset of user command streams collected from working with Microsoft (MS) Word to serve as a test bed. User profiles are first built using MS Word commands and identification takes place using machine learning algorithms. Best performance in terms of both accuracy and Area under the Curve (AUC) for Receiver Operating Characteristic (ROC) curve is reported using Random Forests (RF) and AdaBoost with random forests.

DeepQA is a large-scale natural language processing (NLP) question-and-answer system that responds across a breadth of structured and unstructured data, from hundreds of analytics that are combined with over 50 models, trained through machine learning. After the 2011 historic milestone of defeating the two best human players in the Jeopardy! game show, the technology behind IBM Watson, DeepQA, is undergoing gamification into real-world business problems. Gamifying a business domain for Watson is a composite of functional, content, and training adaptation for nongame play. During domain gamification for medical, financial, government, or any other business, each system change affects the machine-learning process. As opposed to the original Watson Jeopardy!, whose class distribution of positive-to-negative labels is 1:100, in adaptation the computed training instances, question-and-answer pairs transformed into true-false labels, result in a very low positive-to-negative ratio of 1:100 000. Such initial extreme class imbalance during domain gamification poses a big challenge for the Watson machine-learning pipelines. The combination of ingested corpus sets, question-and-answer pairs, configuration settings, and NLP algorithms contribute toward the challenging data state. We propose several data engineering techniques, such as answer key vetting and expansion, source ingestion, oversampling classes, and question set modifications to increase the computed true labels. In addition, algorithm engineering, such as an implementation of the Newton-Raphson logistic regression with a regularization term, relaxes the constraints of class imbalance during training adaptation. We conclude by empirically demonstrating that data and algorithm engineering are complementary and indispensable to overcome the challenges in this first Watson gamification for real-world business problems.

Machine learning (ML) plays a central role in the solution of many security problems, for example enabling malicious and innocent activities to be rapidly and accurately distinguished and appropriate actions to be taken. Unfortunately, a standard assumption in ML - that the training and test data are identically distributed - is typically violated in security applications, leading to degraded algorithm performance and reduced security. Previous research has attempted to address this challenge by developing ML algorithms which are either robust to differences between training and test data or are able to predict and account for these differences. This paper adopts a different approach, developing a class of moving target (MT) defenses that are difficult for adversaries to reverse-engineer, which in turn decreases the adversaries' ability to generate training/test data differences that benefit them. We leverage the coevolutionary relationship between attackers and defenders to derive a simple, flexible MT defense strategy which is optimal or nearly optimal for a broad range of security problems. Case studies involving two distinct cyber defense applications demonstrate that the proposed MT algorithm outperforms standard static methods, offering effective defense against intelligent, adaptive adversaries.

We consider the setting of HTTP traffic over encrypted tunnels, as used to conceal the identity of websites visited by a user. It is well known that traffic analysis (TA) attacks can accurately identify the website a user visits despite the use of encryption, and previous work has looked at specific attack/countermeasure pairings. We provide the first comprehensive analysis of general-purpose TA countermeasures. We show that nine known countermeasures are vulnerable to simple attacks that exploit coarse features of traffic (e.g., total time and bandwidth). The considered countermeasures include ones like those standardized by TLS, SSH, and IPsec, and even more complex ones like the traffic morphing scheme of Wright et al. As just one of our results, we show that despite the use of traffic morphing, one can use only total upstream and downstream bandwidth to identify – with 98% accuracy - which of two websites was visited. One implication of what we find is that, in the context of website identification, it is unlikely that bandwidth-efficient, general-purpose TA countermeasures can ever provide the type of security targeted in prior work.

In network intrusion detection research, one popular strategy for finding attacks is monitoring a network's activity for anomalies: deviations from profiles of normality previously learned from benign traffic, typically identified using tools borrowed from the machine learning community. However, despite extensive academic research one finds a striking gap in terms of actual deployments of such systems: compared with other intrusion detection approaches, machine learning is rarely employed in operational "real world" settings. We examine the differences between the network intrusion detection problem and other areas where machine learning regularly finds much more success. Our main claim is that the task of finding attacks is fundamentally different from these other applications, making it significantly harder for the intrusion detection community to employ machine learning effectively. We support this claim by identifying challenges particular to network intrusion detection, and provide a set of guidelines meant to strengthen future research on anomaly detection.

Poison message failure is a mechanism that has been responsible for large scale failures in both telecommunications and IP networks. The poison message failure can propagate in the network and cause an unstable network. We apply a machine learning, data mining technique in the network fault management area. We use the k-nearest neighbor method to identity the poison message failure. We also propose a "probabilistic" k-nearest neighbor method which outputs a probability distribution about the poison message. Through extensive simulations, we show that the k-nearest neighbor method is very effective in identifying the responsible message type.