Program authorship attribution has implications for the privacy of programmers who wish to contribute code anonymously. While previous work has shown that complete files that are individually authored can be attributed, we show here for the first time that accounts belonging to open source contributors containing short, incomplete, and typically uncompilable fragments can also be effectively attributed.We propose a technique for authorship attribution of contributor accounts containing small source code samples, such as those that can be obtained from version control systems or other direct comparison of sequential versions. We show that while application of previous methods to individual small source code samples yields an accuracy of about 73% for 106 programmers as a baseline, by ensembling and averaging the classification probabilities of a sufficiently large set of samples belonging to the same author we achieve 99% accuracy for assigning the set of samples to the correct author. Through these results, we demonstrate that attribution is an important threat to privacy for programmers even in real-world collaborative environments such as GitHub. Additionally, we propose the use of calibration curves to identify samples by unknown and previously unencountered authors in the open world setting. We show that we can also use these calibration curves in the case that we do not have linking information and thus are forced to classify individual samples directly. This is because the calibration curves allow us to identify which samples are more likely to have been correctly attributed. Using such a curve can help an analyst choose a cut-off point which will prevent most misclassifications, at the cost of causing the rejection of some of the more dubious correct attributions.

Deep ultraviolet wavelengths have been proposed for low-probability-of-detection (LPD) communications, particularly for non-line-of-sight (NLOS) links, because of the increased atmospheric absorption at these wavelengths. Motivated by this favorable feature, we develop a modeling framework to quantitatively study the LPD characteristics of ultraviolet communications (UVC). We then demonstrate the application of our modeling framework by considering various friendly and adversarial system configurations and quantifying the proposed LPD metric (the range at which an adversary can detect communications that uses the minimum power needed to meet given communications performance requirements), as well as investigating the sensitivity of the analysis to various scenario parameters. The results demonstrate the potential for this modeling and analysis approach to provide key insights into the design and operation of LPD NLOS UVC systems.

Network intrusion detection systems (NIDS) are an essential defense for computer networks and the hosts within them. Machine learning (ML) nowadays predominantly serves as the basis for NIDS decision making, where models are tuned to reduce false alarms, increase detection rates, and detect known and unknown attacks. At the same time, ML models have been found to be vulnerable to adversarial examples that undermine the downstream task. In this work, we ask the practical question of whether real-world MLbased NIDS can be circumvented by crafted adversarial flows, and if so, how can they be created. We develop the generative adversarial network (GAN)-based attack algorithm NIDSGAN and evaluate its effectiveness against realistic ML-based NIDS. Two main challenges arise for generating adversarial network traffic flows: (1) the network features must obey the constraints of the domain (i.e., represent realistic network behavior), and (2) the adversary must learn the decision behavior of the target NIDS without knowing its model internals (e.g., architecture and meta-parameters) and training data. Despite these challenges, the NIDSGAN algorithm generates highly realistic adversarial traffic flows that evade ML-based NIDS. We evaluate our attack algorithm against two state-of-the-art DNNbased NIDS in whitebox, blackbox, and restricted-blackbox threat models and achieve success rates which are on average 99%, 85%, and 70%, respectively. We also show that our attack algorithm can evade NIDS based on classical ML models including logistic regression, SVM, decision trees and KNNs, with a success rate of 70% on average. Our results demonstrate that deploying ML-based NIDS

Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs in the modeled domains. Diverse domains such as networks and phishing have domain constraints-complex relationships between features that an adversary must satisfy for an attack to be realized (in addition to any adversary-specific goals). In this paper, we explore how domain constraints limit adversarial capabilities and how adversaries can adapt their strategies to create realistic (constraint-compliant) examples. In this, we develop techniques to learn domain constraints from data, and show how the learned constraints can be integrated into the adversarial crafting process. We evaluate the efficacy of our approach in network intrusion and phishing datasets and find:(1) up to 82% of adversarial examples produced by state-of-the-art crafting algorithms violate domain constraints, (2) domain constraints are robust to adversarial examples; enforcing constraints yields an increase in model accuracy by up to 34%. We observe not only that adversaries must alter inputs to satisfy domain constraints, but that these constraints make the generation of valid adversarial examples far more challenging.

No abstract