Related papers: Adversarial Deep Reinforcement Learning based Adap…
Many defensive measures in cyber security are still dominated by heuristics, catalogs of standard procedures, and best practices. Considering the case of data backup strategies, we aim towards mathematically modeling the underlying threat…
Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In…
It is challenging for a security analyst to detect or defend against cyber-attacks. Moreover, traditional defense deployment methods require the security analyst to manually enforce the defenses in the presence of uncertainties about the…
Autonomous UAV navigation using reinforcement learning (RL) is vulnerable to adversarial attacks that manipulate sensor inputs, potentially leading to unsafe behavior and mission failure. Although robust RL methods provide partial…
Adversarial Patrolling games form a subclass of Security games where a Defender moves between locations, guarding vulnerable targets. The main algorithmic problem is constructing a strategy for the Defender that minimizes the worst damage…
Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…
Protecting against multi-step attacks of uncertain duration and timing forces defenders into an indefinite, always ongoing, resource-intensive response. To effectively allocate resources, a defender must be able to analyze multi-step…
To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…
We consider the trade-off problem between exploration and exploitation under finite discounted Markov Decision Process, where the state transition matrix of the underlying environment stays unknown. We propose a double Thompson sampling…
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack…
Advanced persistent threats (APT) combine a variety of different attack forms ranging from social engineering to technical exploits. The diversity and usual stealthiness of APT turns them into a central problem of contemporary practical…
The need for autonomous and adaptive defense mechanisms has become paramount in the rapidly evolving landscape of cyber threats. Multi-Agent Deep Reinforcement Learning (MADRL) presents a promising approach to enhancing the efficacy and…
In this paper, we investigate the dynamics-aware adversarial attack problem of adaptive neural networks. Most existing adversarial attack algorithms are designed under a basic assumption -- the network architecture is fixed throughout the…
In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would…
Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured…
We consider the problem of tracking an adversarial state sequence in a linear dynamical system subject to adversarial disturbances and loss functions, generalizing earlier settings in the literature. To this end, we develop three…
Reinforcement learning in complex environments may require supervision to prevent the agent from attempting dangerous actions. As a result of supervisor intervention, the executed action may differ from the action specified by the policy.…
Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…
Deploying autonomous driving systems requires robustness against long-tail scenarios that are rare but safety-critical. While adversarial training offers a promising solution, existing methods typically decouple scenario generation from…
Deep learning models are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations on benign images. Many existing adversarial attack methods have achieved great white-box attack performance, but…