Biblio
Advanced persistent threats (APT) have increased in recent times as a result of the rise in interest by nation-states and sophisticated corporations to obtain high profile information. Typically, APT attacks are more challenging to detect since they leverage zero-day attacks and common benign tools. Furthermore, these attack campaigns are often prolonged to evade detection. We leverage an approach that uses a provenance graph to obtain execution traces of host nodes in order to detect anomalous behavior. By using the provenance graph, we extract features that are then used to train an online adaptive metric learning. Online metric learning is a deep learning method that learns a function to minimize the separation between similar classes and maximizes the separation between dis-similar instances. We compare our approach with baseline models and we show our method outperforms the baseline models by increasing detection accuracy on average by 11.3 % and increases True positive rate (TPR) on average by 18.3 %.
In the past decades, learning an effective distance metric between pairs of instances has played an important role in the classification and retrieval task, for example, the person identification or malware retrieval in the IoT service. The core motivation of recent efforts focus on improving the metric forms, and already showed promising results on the various applications. However, such models often fail to produce a reliable metric on the ambiguous test set. It happens mainly due to the sampling process of the training set, which is not representative of the distribution of the negative samples, especially the examples that are closer to the boundary of different categories (also called hard negative samples). In this paper, we focus on addressing such problems and propose an adaptive margin deep adversarial metric learning (AMDAML) framework. It exploits numerous common negative samples to generate potential hard (adversarial) negatives and applies them to facilitate robust metric learning. Apart from the previous approaches that typically depend on the search or data augmentation to find hard negative samples, the generation of adversarial negative instances could avoid the limitation of domain knowledge and constraint pairs' amount. Specifically, in order to prevent over fitting or underfitting during the training step, we propose an adaptive margin loss that preserves a flexible margin between the negative (include the adversarial and original) and positive samples. We simultaneously train both the adversarial negative generator and conventional metric objective in an adversarial manner and learn the feature representations that are more precise and robust. The experimental results on practical data sets clearly demonstrate the superiority of AMDAML to representative state-of-the-art metric learning models.
With an increase in targeted attacks such as advanced persistent threats (APTs), enterprise system defenders require comprehensive frameworks that allow them to collaborate and evaluate their defense systems against such attacks. MITRE has developed a framework which includes a database of different kill-chains, tactics, techniques, and procedures that attackers employ to perform these attacks. In this work, we leverage natural language processing techniques to extract attacker actions from threat report documents generated by different organizations and automatically classify them into standardized tactics and techniques, while providing relevant mitigation advisories for each attack. A naïve method to achieve this is by training a machine learning model to predict labels that associate the reports with relevant categories. In practice, however, sufficient labeled data for model training is not always readily available, so that training and test data come from different sources, resulting in bias. A naïve model would typically underperform in such a situation. We address this major challenge by incorporating an importance weighting scheme called bias correction that efficiently utilizes available labeled data, given threat reports, whose categories are to be automatically predicted. We empirically evaluated our approach on 18,257 real-world threat reports generated between year 2000 and 2018 from various computer security organizations to demonstrate its superiority by comparing its performance with an existing approach.
This paper describes a data driven approach to studying the science of cyber security (SoS). It argues that science is driven by data. It then describes issues and approaches towards the following three aspects: (i) Data Driven Science for Attack Detection and Mitigation, (ii) Foundations for Data Trustworthiness and Policy-based Sharing, and (iii) A Risk-based Approach to Security Metrics. We believe that the three aspects addressed in this paper will form the basis for studying the Science of Cyber Security.
Language vector space models (VSMs) have recently proven to be effective across a variety of tasks. In VSMs, each word in a corpus is represented as a real-valued vector. These vectors can be used as features in many applications in machine learning and natural language processing. In this paper, we study the effect of vector space representations in cyber security. In particular, we consider a passive traffic analysis attack (Website Fingerprinting) that threatens users' navigation privacy on the web. By using anonymous communication, Internet users (such as online activists) may wish to hide the destination of web pages they access for different reasons such as avoiding tyrant governments. Traditional website fingerprinting studies collect packets from the users' network and extract features that are used by machine learning techniques to reveal the destination of certain web pages. In this work, we propose the packet to vector (P2V) approach where we model website fingerprinting attack using word vector representations. We show how the suggested model outperforms previous website fingerprinting works.