Smartphones and mobile tablets are rapidly becoming indispensable in daily life. Android has been the most popular mobile operating system since 2012. However, owing to the open nature of Android, countless malwares are hidden in a large number of benign apps in Android markets that seriously threaten Android security. Deep learning is a new area of machine learning research that has gained increasing attention in artificial intelligence. In this study, we propose to associate the features from the static analysis with features from dynamic analysis of Android apps and characterize malware using deep learning techniques. We implement an online deep-learning-based Android malware detection engine (DroidDetector) that can automatically detect whether an app is a malware or not. With thousands of Android apps, we thoroughly test DroidDetector and perform an indepth analysis on the features that deep learning essentially exploits to characterize malware. The results show that deep learning is suitable for characterizing Android malware and especially effective with the availability of more training data. DroidDetector can achieve 96.76% detection accuracy, which outperforms traditional machine learning techniques. An evaluation of ten popular anti-virus softwares demonstrates the urgency of advancing our capabilities in Android malware detection.

Abstract-During the past decade, the packet classification problem has been widely studied to accelerate network applications such as access control, traffic engineering and intrusion detection. In our research, we found that although a great number of packet classification algorithms have been proposed in recent years, unfortunately most of them stagnate in mathematical analysis or software simulation stages and few of them have been implemented in commercial products as a generic solution. To fill the gap between theory and practice, in this paper, we propose a novel packet classification algorithm named HyperSplit. Compared to the well-known HiCuts and HSM algorithms, HyperSplit achieves superior performance in terms of classification speed, memory usage and preprocessing time. The practicability of the proposed algorithm is manifested by two facts in our test: HyperSplit is the only algorithm that can successfully handle all the rule sets; HyperSplit is also the only algorithm that reaches more than 6Gbps throughput on the Octeon3860 multi-core platform when tested with 64-byte Ethernet packets against 10K ACL rules.

Abstract-Pattern matching is one of the most important components for the content inspection based applications of network security, and it requires well designed algorithms and architectures to keep up with the increasing network speed. For most of the solutions, AC and its derivative algorithms are widely used. They are based on the DFA model but utilize large amount of memory because of so many transition rules. An algorithm, called ACC, is presented in this paper for multiple pattern matching. It uses a novel model, namely cached deterministic finite automate (CDFA). In ACC, by using CDFA, only 4.1% transition rules for ClamAV (20.8% for Snort) are needed to represent the same function using DFA built by AC. This paper also proposes a new scheme named next-state addressing (NSA) to store and access transition rules of DFA in memory. Using this method, transition rules can be efficiently stored and directly accessed. Finally the architecture for multiple pattern matching is optimized by several approaches. Experiments show our architecture can achieve matching speed faster than 10Gbps with very efficient memory utilization, i.e., 81KB memory for 1.8K Snort rules with total 29K characters, and 9.5MB memory for 50K ClamAV rules with total 4.44M characters. A single architecture is memory efficient for large pattern set, and it is possible to support more than 10M patterns with at most half amount of the memory utilization compared to the state-of-the-art architectures.

No abstract

No abstract