Publications

Abstract not provided.

In many organizations, intrusion detection and other related systems are tuned to generate security alerts, which are then manually inspected by cyber-security analysts. These analysts often devote a large portion of time to inspecting these alerts, most of which are innocuous. Thus, it would be greatly beneficial to reduce the number of innocuous alerts, allowing analysts to utilize their time and skills for other aspects of cyber defense. In this work, we devise several simple, fast, and easily understood models to cut back this manual inspection workload, while maintaining high true positive and true negative rates. We demonstrate their effectiveness on real data, and discuss their potential utility in application by others.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

As cyber monitoring capabilities expand and data rates increase, cyber security analysts must filter through an increasing number of alerts in order to identify potential intrusions on the network. This process is often manual and time-consuming, which limits the number of alerts an analyst can process. This generation of a vast number of alerts without any kind of ranking or prioritization is often referred to as alert desensitization [1]. This is the phenomenon where competent analysts become so numbed by the barrage of false positives that they are unable to identify the true positives, leading to unfortunate breaches. Our goal is to alleviate alert desensitization by placing the most important alerts at the front of the queue. With less time and energy expended investigating false positives, critical alerts may not be overlooked allowing timely responses to potential breaches. This paper discusses the use of supervised machine learning to rank these cyber security alerts to ensure that an analyst's time and energy are focused on the most important alerts.

As cyber monitoring capabilities expand and data rates increase, cyber security analysts must filter through an increasing number of alerts in order to identify potential intrusions on the network. This process is often manual and time-consuming, which limits the number of alerts an analyst can process. This generation of a vast number of alerts without any kind of ranking or prioritization is often referred to as alert desensitization [1]. This is the phenomenon where competent analysts become so numbed by the barrage of false positives that they are unable to identify the true positives, leading to unfortunate breaches. Our goal is to alleviate alert desensitization by placing the most important alerts at the front of the queue. With less time and energy expended investigating false positives, critical alerts may not be overlooked allowing timely responses to potential breaches. This paper discusses the use of supervised machine learning to rank these cyber security alerts to ensure that an analyst's time and energy are focused on the most important alerts.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Analyzing mobile applications for malicious behavior is an important area of re- search, and is made di cult, in part, by the increasingly large number of appli- cations available for the major operating systems. There are currently over 1.2 million apps available in both the Google Play and Apple App stores (the respec- tive o cial marketplaces for the Android and iOS operating systems)[1, 2]. Our research provides two large-scale analysis tools to aid in the detection and analysis of mobile malware. The rst tool we present, Andlantis, is a scalable dynamic analysis system capa- ble of processing over 3000 Android applications per hour. Traditionally, Android dynamic analysis techniques have been relatively limited in scale due to the compu- tational resources required to emulate the full Android system to achieve accurate execution. Andlantis is the most scalable Android dynamic analysis framework to date, and is able to collect valuable forensic data, which helps reverse-engineers and malware researchers identify and understand anomalous application behavior. We discuss the results of running 1261 malware samples through the system, and provide examples of malware analysis performed with the resulting data. While techniques exist to perform static analysis on a large number of appli- cations, large-scale analysis of iOS applications has been relatively small scale due to the closed nature of the iOS ecosystem, and the di culty of acquiring appli- cations for analysis. The second tool we present, iClone, addresses the challenges associated with iOS research in order to detect application clones within a dataset of over 20,000 iOS applications.

Abstract not provided.

Abstract not provided.