Biblio

Intrusion Detection Systems (IDS) have been in existence for many years now, but they fall short in efficiently detecting zero-day attacks. This paper presents an organic combination of Semantic Link Networks (SLN) and dynamic semantic graph generation for the on the fly discovery of zero-day attacks using the Spark Streaming platform for parallel detection. In addition, a minimum redundancy maximum relevance (MRMR) feature selection algorithm is deployed to determine the most discriminating features of the dataset. Compared to previous studies on zero-day attack identification, the described method yields better results due to the semantic learning and reasoning on top of the training data and due to the use of collaborative classification methods. We also verified the scalability of our method in a distributed environment.

Summary form only given. Symbolic execution is a systematic program analysis technique which explores multiple program behaviors all at once by collecting and solving symbolic path conditions over program paths. The technique has been recently extended with probabilistic reasoning. This approach computes the conditions to reach target program events of interest and uses model counting to quantify the fraction of the input domain satisfying these conditions thus computing the probability of event occurrence. This probabilistic information can be used for example to compute the reliability of an aircraft controller under different wind conditions (modeled probabilistically) or to quantify the leakage of sensitive data in a software system, using information theory metrics such as Shannon entropy. In this talk we review recent advances in symbolic execution and probabilistic reasoning and we discuss how they can be used to ensure the safety and security of software systems.

The world is witnessing a remarkable increase in the usage of video surveillance systems. Besides fulfilling an imperative security and safety purpose, it also contributes towards operations monitoring, hazard detection and facility management in industry/smart factory settings. Most existing surveillance techniques use hand-crafted features analyzed using standard machine learning pipelines for action recognition and event detection. A key shortcoming of such techniques is the inability to learn from unlabeled video streams. The entire video stream is unlabeled when the requirement is to detect irregular, unforeseen and abnormal behaviors, anomalies. Recent developments in intelligent high-level video analysis have been successful in identifying individual elements in a video frame. However, the detection of anomalies in an entire video feed requires incremental and unsupervised machine learning. This paper presents a novel approach that incorporates high-level video analysis outcomes with incremental knowledge acquisition and self-learning for autonomous video surveillance. The proposed approach is capable of detecting changes that occur over time and separating irregularities from re-occurrences, without the prerequisite of a labeled dataset. We demonstrate the proposed approach using a benchmark video dataset and the results confirm its validity and usability for autonomous video surveillance.

This paper describes a data driven approach to studying the science of cyber security (SoS). It argues that science is driven by data. It then describes issues and approaches towards the following three aspects: (i) Data Driven Science for Attack Detection and Mitigation, (ii) Foundations for Data Trustworthiness and Policy-based Sharing, and (iii) A Risk-based Approach to Security Metrics. We believe that the three aspects addressed in this paper will form the basis for studying the Science of Cyber Security.

Expressing and matching the security policy of each participant accurately is the precondition to construct a secure service composition. Most schemes presently use syntactic approaches to represent and match the security policy for service composition process, which is prone to result in false negative because of lacking semantics. In this paper, a novel approach based on semantics is proposed to express and match the security policies in service composition. Through constructing a general security ontology, the definition method and matching algorithm of the semantic security policy for service composition are presented, and the matching problem of policy is translated into the subsumption reasoning problem of semantic concept. Both the theoretical analysis and experimental evaluation show that, the proposed approach can present the necessary semantic information in the representation of policy and effectively improve the accuracy of matching result, thus overcome the deficiency of the syntactic approaches, and can also simplify the definition and management of the policy at the same time, which thereby provides a more effective solution for building the secure service composition based on security policy.

Interface-confinement is a common mechanism that secures untrusted code by executing it inside a sandbox. The sandbox limits (confines) the code's interaction with key system resources to a restricted set of interfaces. This practice is seen in web browsers, hypervisors, and other security-critical systems. Motivated by these systems, we present a program logic, called System M, for modeling and proving safety properties of systems that execute adversary-supplied code via interface-confinement. In addition to using computation types to specify effects of computations, System M includes a novel invariant type to specify the properties of interface-confined code. The interpretation of invariant type includes terms whose effects satisfy an invariant. We construct a step-indexed model built over traces and prove the soundness of System M relative to the model. System M is the first program logic that allows proofs of safety for programs that execute adversary-supplied code without forcing the adversarial code to be available for deep static analysis. System M can be used to model and verify protocols as well as system designs. We demonstrate the reasoning principles of System M by verifying the state integrity property of the design of Memoir, a previously proposed trusted computing system.

This study describes and evaluates a novel trust model for a range of collaborative applications. The model assumes that humans routinely choose to trust their peers by relying on few recurrent presumptions, which are domain independent and which form a recognisable trust expertise. We refer to these presumptions as trust schemes, a specialised version of Walton's argumentation schemes. Evidence is provided about the efficacy of trust schemes using a detailed experiment on an online community of 80,000 members. Results show how proposed trust schemes are more effective in trust computation when they are combined together and when their plausibility in the selected context is considered.

Alex Endert's dissertation "Semantic Interaction for Visual Analytics: Inferring Analytical Reasoning for Model Steering" described semantic interaction, a user interaction methodology for visual analytics (VA). It showed that user interaction embodies users' analytic process and can thus be mapped to model-steering functionality for "human-in-the-loop" system design. The dissertation contributed a framework (or pipeline) that describes such a process, a prototype VA system to test semantic interaction, and a user evaluation to demonstrate semantic interaction's impact on the analytic process. This research is influencing current VA research and has implications for future VA research.

Multiple Security Domains Nondeducibility, MSDND, yields results even when the attack hides important information from electronic monitors and human operators. Because MSDND is based upon modal frames, it is able to analyze the event system as it progresses rather than relying on traces of the system. Not only does it provide results as the system evolves, MSDND can point out attacks designed to be missed in other security models. This work examines information flow disruption attacks such as Stuxnet and formally explains the role that implicit trust in the cyber security of a cyber physical system (CPS) plays in the success of the attack. The fact that the attack hides behind MSDND can be used to help secure the system by modifications to break MSDND and leave the attack nowhere to hide. Modal operators are defined to allow the manipulation of belief and trust states within the model. We show how the attack hides and uses the operator's trust to remain undetected. In fact, trust in the CPS is key to the success of the attack.

Although current Internet operations generate voluminous data, they remain largely oblivious of traffic data semantics. This poses many inefficiencies and challenges due to emergent or anomalous behavior impacting the vast array of Internet elements such as services and protocols. In this paper, we propose a Data Semantics Management System (DSMS) for learning Internet traffic data semantics to enable smarter semantics- driven networking operations. We extract networking semantics and build and utilize a dynamic ontology of network concepts to better recognize and act upon emergent or abnormal behavior. Our DSMS utilizes: (1) Latent Dirichlet Allocation algorithm (LDA) for latent features extraction and semantics reasoning; (2) big tables as a cloud-like data storage technique to maintain large-scale data; and (3) Locality Sensitive Hashing algorithm (LSH) for reducing data dimensionality. Our preliminary evaluation using real Internet traffic shows the efficacy of DSMS for learning behavior of normal and abnormal traffic data and for accurately detecting anomalies at low cost.
 

The distinctive features of mobile ad hoc networks (MANETs), including dynamic topology and open wireless medium, may lead to MANETs suffering from many security vulnerabilities. In this paper, using recent advances in uncertain reasoning that originated from the artificial intelligence community, we propose a unified trust management scheme that enhances the security in MANETs. In the proposed trust management scheme, the trust model has two components: trust from direct observation and trust from indirect observation. With direct observation from an observer node, the trust value is derived using Bayesian inference, which is a type of uncertain reasoning when the full probability model can be defined. On the other hand, with indirect observation, which is also called secondhand information that is obtained from neighbor nodes of the observer node, the trust value is derived using the Dempster-Shafer theory (DST), which is another type of uncertain reasoning when the proposition of interest can be derived by an indirect method. By combining these two components in the trust model, we can obtain more accurate trust values of the observed nodes in MANETs. We then evaluate our scheme under the scenario of MANET routing. Extensive simulation results show the effectiveness of the proposed scheme. Specifically, throughput and packet delivery ratio (PDR) can be improved significantly with slightly increased average end-to-end delay and overhead of messages.

We propose 10 challenges for making automation components into effective "team players" when they interact with people in significant ways. Our analysis is based on some of the principles of human-centered computing that we have developed individually and jointly over the years, and is adapted from a more comprehensive examination of common ground and coordination.