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 identifywith 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, generalpurpose TA countermeasures can ever provide the type of security targeted in prior work.

The convolutional neural network (CNN) architecture is increasingly being applied to new domains, such as malware detection, where it is able to learn malicious behavior from raw bytes extracted from executables. These architectures reach impressive performance with no feature engineering effort involved, but their robustness against active attackers is yet to be understood. Such malware detectors could face a new attack vector in the form of adversarial interference with the classification model. Existing evasion attacks intended to cause misclassification on test-time instances, which have been extensively studied for image classifiers, are not applicable because of the input semantics that prevents arbitrary changes to the binaries. This paper explores the area of adversarial examples for malware detection. By training an existing model on a production-scale dataset, we show that some previous attacks are less effective than initially reported, while simultaneously highlighting architectural weaknesses that facilitate new attack strategies for malware classification. Finally, we explore how generalizable different attack strategies are, the trade-offs when aiming to increase their effectiveness, and the transferability of single-step attacks.

No abstract

Deep packet inspection (DPI) technologies provide muchneeded visibility and control of network traffic using portindependent protocol identification, where a network flow is labeled with its application-layer protocol based on packet contents. In this paper, we provide the first comprehensive evaluation of a large set of DPI systems from the point of view of protocol misidentification attacks, in which adversaries on the network attempt to force the DPI to mislabel connections. Our approach uses a new cryptographic primitive called format-transforming encryption (FTE), which, intuitively, extends conventional symmetric encryption with the ability to transform the ciphertext into a format of our choosing. We design an FTE-based record layer that can encrypt arbitrary application-layer traffic, and we experimentally show that this forces misidentification for all of the evaluated DPI systems. This set includes a proprietary, enterprise-class DPI system used by large corporations and nation-states. We also show that using FTE as a proxy system incurs no latency overhead and only 16% more bandwidth than standard SSH tunnels. Finally, we integrate our FTE proxy into Tor and demonstrate that it evades realworld censorship by the Great Firewall of China.

This paper addresses the problem of detecting masquerading, a security attack in which an intruder assumes the identity of a legitimate user. Many approaches based on Hidden Markov Models and various forms of Finite State Automata have been proposed to solve this problem. The novelty of our approach results from the application of techniques used in bioinformatics for a pair-wise sequence alignment to compare the monitored session with past user behavior. Our algorithm uses a semi-global alignment and a unique scoring system to measure similarity between a sequence of commands produced by a potential intruder and the user signature, which is a sequence of commands collected from a legitimate user. We tested this algorithm on the standard intrusion data collection set. As discussed in the paper, the results of the test showed that the described algorithm yields a promising combination of intrusion detection rate and false positive rate, when compared to published intrusion detection algorithms.