No description available.

This dissertation investigates using instantaneous battery current sensing techniques as a means of detecting IEEE 802.15.1 Bluetooth and 802.11b (Wi-Fi) attacks and anomalous activity on small mobile wireless devices. This research explores alternative intrusion detection methods in an effort to better understand computer networking threats. This research applies to Personal Digital Assistants (PDAs) and smart phones, operating with sensing software in wireless network environments to relay diagnostic battery readings and threshold breaches to indicate possible battery exhaustion attack, intrusion, virus, and worm activity detections. The system relies on host-based software to collect smart battery data to sense instantaneous current characteristics of anomalous network activity directed against small mobile devices. This effort sought to develop a methodology, design and build a net-centric system, and then further explore this non-traditional intrusion detection system (IDS) approach. This research implements the Battery-Sensing Intrusion Protection System (B-SIPS) client detection capabilities for small mobile devices, a server-based Correlation Intrusion Detection Engine (CIDE) for attack correlation with Snort's network-based IDS, device power profiling, graph views, security administrator alert notification, and a database for robust data storage. Additionally, the server-based CIDE provides the interface and filtering tools for a security administrator to further mine our database and conduct forensic analysis. A separate system was developed using a digital oscilloscope to observe Bluetooth, Wi-Fi, and blended attack traces and to create unique signatures. The research endeavor makes five significant contributions to the security field of intrusion detection. First, this B-SIPS work creates an effective intrusion detection approach that can operate on small, mobile host devices in networking environments to sense anomalous patterns in instantaneous battery current as an indicator of malicious activity using an innovative Dynamic Threshold Calculation (DTC) algorithm. Second, the Current Attack Signature Identification and Matching System (CASIMS) provides a means for high resolution current measurements and supporting analytical tools. This system investigates Bluetooth, Wi-Fi, and blended exploits using an oscilloscope to gather high fidelity data. Instantaneous current changes were examined on mobile devices during representative attacks to determine unique attack traces and recognizable signatures. Third, two B-SIPS supporting theoretical models are presented to investigate static and dynamic smart battery polling. These analytical models are employed to examine smart battery characteristics to support the theoretical intrusion detection limits and capabilities of B-SIPS. Fourth, a new genre of attack, known as a Battery Polling Cycle Timing Attack, is introduced. Today's smart battery technology polling rates are designed to support Advanced Power Management needs. Every PDA and smart phone has a polling rate that is determined by the device and smart battery original equipment manufacturers. If an attacker knows the precise timing of the polling rate of the battery's chipset, then the attacker could attempt to craft intrusion packets to arrive within those limited time windows and between the battery's polling intervals. Fifth, this research adds to the body of knowledge about non-traditional attack sensing and correlation by providing a component of an intrusion detection strategy. This work expands today's research knowledge towards a more robust multilayered network defense by creating a novel design and methodology for employing mobile computing devices as a first line of defense to improve overall network security and potentially through extension to other communication mediums in need of defensive capabilities. Mobile computing and communications devices such as PDAs, smart phones, and ultra small general purpose computing devices are the typical targets for the results of this work. Additionally, field-deployed battery operated sensors and sensor networks will also benefit by incorporating security mechanisms developed and described here. / Ph. D.

There have been many studies performing experiments that showcase the potential of machine learning solutions for intrusion detection, but their experimental approaches are non-transparent and vague, making it difficult to replicate their trained methods and results. In this thesis we exemplify a healthier experimental methodology. A survey was performed to investigate evaluation metrics. Three experiments implementing and benchmarking machine learning classifiers, using different optimization techniques, were performed to set up a frame of reference for future work, as well as signify the importance of using descriptive metrics and disclosing implementation. We found a set of metrics that more accurately describes the models, and we found guidelines that we would like future researchers to fulfill in order to make their work more comprehensible. For future work we would like to see more discussion regarding metrics, and a new dataset that is more generalizable.

Network security has become a vital part for computer networks to ensure that they operate as expected. With many of today's services relying on networks it is of great importance that the usage of networks are not being compromised. One way to increase the security of a computer network is to implement a Network Intrusion Detection System (NIDS). This system monitors the traffic sent to, from and within the network. This study investigates how a NIDS called SNORT with different configurations handles common network attacks. The knowledge of how SNORT managed the attacks is used to evaluate and indicate the vulnerability of different SNORT configurations. Different approaches on both how to bypass SNORT and how to detect attacks are described both theoretically, and practically with experiments. This study concludes that a carefully prepared configuration is the factor for SNORT to perform well in network intrusion detection.

In the recent years, connected surveillance systems have been witnessing an unprecedented evolution owing to the advancements in internet of things and deep learning technologies. However, vulnerabilities to various kinds of attacks both at the cyber network-level and at the physical worldlevel are also rising. This poses danger not only to the devices but also to human life and property. The goal of this thesis is to enhance the security of an internet of things, focusing on connected video-based surveillance systems, by proposing multiple novel solutions to address security issues at the cyber network-level and to defend such systems at the physical world-level. In order to enhance security at the cyber network-level, this thesis designs and develops solutions to detect network intrusions in an internet of things such as surveillance cameras. The first solution is a novel method for network flow features transformation, named TempoCode. It introduces a temporal codebook-based encoding of flow features based on capturing the key patterns of benign traffic in a learnt temporal codebook. The second solution takes an unsupervised learning-based approach and proposes four methods to build efficient and adaptive ensembles of neural networks-based autoencoders for intrusion detection in internet of things such as surveillance cameras. To address the physical world-level attacks, this thesis studies, for the first time to the best of our knowledge, adversarial patches-based attacks against a convolutional neural network (CNN)- based surveillance system designed for vehicle make and model recognition (VMMR). The connected video-based surveillance systems that are based on deep learning models such as CNNs are highly vulnerable to adversarial machine learning-based attacks that could trick and fool the surveillance systems. In addition, this thesis proposes and evaluates a lightweight defense solution called SIHFR to mitigate the impact of such adversarial-patches on CNN-based VMMR systems, leveraging the symmetry in vehicles’ face images. The experimental evaluations on recent realistic intrusion detection datasets prove the effectiveness of the developed solutions, in comparison to state-of-the-art, in detecting intrusions of various types and for different devices. Moreover, using a real-world surveillance dataset, we demonstrate the effectiveness of the SIHFR defense method which does not require re-training of the target VMMR model and adds only a minimal overhead. The solutions designed and developed in this thesis shall pave the way forward for future studies to develop efficient intrusion detection systems and adversarial attacks mitigation methods for connected surveillance systems such as VMMR.

No description available.

A problem in computer security is identification of attack signatures in network packets. An attack signature is a pattern of bits that characterizes a particular attack. Because there are many kinds of attacks, there are potentially many attack signatures. Furthermore, attackers may seek to avoid detection by altering the attack mechanism so that the bit pattern presented differs from the known signature. Thus, recognizing attack signatures is a problem in approximate string matching. The time to perform an approximate string match depends upon the length of the string and the number of patterns. For constant string length, the time to matchnpatterns is approximatelyO(n); the time increases approximately linearly as the number of patterns increases. A binary cellular automaton is a discrete, deterministic system of cells in which each cell can have one of two values. Cellular automata have the property that the next state of each cell can be evaluated independently of the others. If there is a processing element for each cell, the next states of all cells in a cellular automaton can be computed simultaneously. Because there is no programming paradigm for cellular automata, cellular automata to perform specific functions are createdad hocby hand or discovered using search methods such as genetic algorithms. This research has identified, through evolution by genetic algorithm, cellular automata that can perform approximate string matching for more than one pattern while operating in constant time with respect to the number of patterns, and in the presence of noise. Patterns were recognized by using the bits of a network packet payload as the initial state of a cellular automaton. After a predetermined number of cycles, the ones density of the cellular automaton was computed. Packets for which the ones density was below an experimentally determined threshold were identified as target packets. Six different cellular automaton rules were tested against a corpus of 7.2 million TCP packets in the IDEval data set. No rule produced false negative results, and false positive results were acceptably low.

ITC/USA 2011 Conference Proceedings / The Forty-Seventh Annual International Telemetering Conference and Technical Exhibition / October 24-27, 2011 / Bally's Las Vegas, Las Vegas, Nevada / iNet is a project aimed at improving and modernizing telemetry systems by moving from a link to a networking solution. Changes introduce new risks and vulnerabilities. The nature of the security of the telemetry system changes when the elements are in an Ethernet and TCP/IP network configuration. The network will require protection from intrusion and malware that can be initiated internal to, or external of the network boundary. In this paper we will discuss how to detect and counter FTP password attacks using the Hidden Markov Model for intrusion detection. We intend to discover and expose the more subtle iNet network vulnerabilities and make recommendations for a more secure telemetry environment.

Computer networks are already ubiquitous in people’s lives and work and network security is becoming a critical part. A simple firewall, which can only scan the bottom four OSI layers, cannot satisfy all security requirements. An intrusion detection system (IDS) with deep packet inspection, which can filter all seven OSI layers, is becoming necessary for more and more networks. However, the processing throughputs of the IDSs are far behind the current network speed. People have begun to improve the performance of the IDSs by implementing them on different hardware platforms, such as Field-Programmable Gate Array (FPGA) or some special network processors. Nevertheless, all of these options are either less flexible or more expensive to deploy. This research focuses on some possibilities of implementing a parallelized IDS on a general computer environment based on Snort, which is the most popular open-source IDS at the moment. In this thesis, some possible methods have been analyzed for the parallelization of the pattern-matching engine based on a multicore computer. However, owing to the small granularity of the network packets, the pattern-matching engine of Snort is unsuitable for parallelization. In addition, a pipelined structure of Snort has been implemented and analyzed. The universal packet capture API - LibPCAP has been modified for a new feature, which can capture a packet directly to an external buffer. Then, the performance of the pipelined Snort can have an improvement up to 60% on an Intel i7 multicore computer for jumbo frames. A primary limitation is on the memory bandwidth. With a higher bandwidth, the performance of the parallelization can be further improved.

The rapid growth and deployment of network technologies and Internet services has made security and management of networks a challenging research problem. This growth is accompanied by an exponential growth in the number of network attacks, which have become more complex, more organized, more dynamic, and more severe than ever. Current network protection techniques are static, slow in responding to attacks, and inefficient due to the large number of false alarms. Attack detection systems can be broadly classified as being signature-based, classification-based, or anomaly-based. In this dissertation, I present a multi-level anomaly based autonomic network defense system which can efficiently detect both known and unknown types of network attacks with a high detection rate and low false alarms. The system uses autonomic computing to automate the control and management of multi-level intrusion detection system and integrate the different components of the system. The system defends the network by detecting anomalies in network operations that may have been caused by network attacks. Like other anomaly detection systems, AND captures a profile of normal network behavior.In this dissertation, I introduce experimental results that evaluate the effectiveness and performance of the multi-level anomaly based autonomic network intrusion detection system in detecting network attacks. The system consist of monitoring modules, feature aggregation and correlation modules, behavior analysis modules, decision fusion module, global visualization module, risk and impact analysis module, action module, attack classification module, and the adaptive learning module. I have successfully implemented a prototype system based on my multi-level anomaly based approach. The experimental results and evaluation of our prototype show that our multi-level intrusion detection system can efficiently and effectively detect and protect against any type of network attacks known or unknown in real-time. Furthermore, the overhead of our approach is insignificant on the normal network operations and services.