Related papers: Learning Adversary Behavior in Security Games: A P…
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact…
This paper addresses a significant gap in Autonomous Cyber Operations (ACO) literature: the absence of effective edge-blocking ACO strategies in dynamic, real-world networks. It specifically targets the cybersecurity vulnerabilities of…
Cyber-security is an important societal concern. Cyber-attacks have increased in numbers as well as in the extent of damage caused in every attack. Large organizations operate a Cyber Security Operation Center (CSOC), which form the first…
Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because strategies interact with each other and change. Most previous work focuses on…
Existing language agents often encounter difficulties in dynamic adversarial games due to poor strategic reasoning. To mitigate this limitation, a promising approach is to allow agents to learn from game interactions automatically, without…
Cyber deception is an emerging proactive defense strategy to counter increasingly sophisticated attacks such as Advanced Persistent Threats (APTs) by misleading and distracting attackers from critical assets. However, since deception…
Machine learning models, especially neural network (NN) classifiers, are widely used in many applications including natural language processing, computer vision and cybersecurity. They provide high accuracy under the assumption of…
Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where…
Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However,…
Safe learning of locomotion skills is still an open problem. Indeed, the intrinsically unstable nature of the open-loop dynamics of locomotion systems renders naive learning from scratch prone to catastrophic failures in the real world. In…
Like many other tasks involving neural networks, Speech Recognition models are vulnerable to adversarial attacks. However recent research has pointed out differences between attacks and defenses on ASR models compared to image models.…
Multi-Agent Reinforcement Learning (MARL) considers settings in which a set of coexisting agents interact with one another and their environment. The adaptation and learning of other agents induces non-stationarity in the environment…
DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an…
We introduce an online learning algorithm for computing adaptive resource allocation policies against strategic ecological adversaries with unknown behavioral models and partial observability. Our setting addresses a fundamental limitation…
We study the generalization error of randomized learning algorithms -- focusing on stochastic gradient descent (SGD) -- using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all…
In the recent years, the problem of identifying suspicious behavior has gained importance and identifying this behavior using computational systems and autonomous algorithms is highly desirable in a tactical scenario. So far, the solutions…
Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…
Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…
Adversarial Machine Learning (AML) is emerging as a major field aimed at protecting machine learning (ML) systems against security threats: in certain scenarios there may be adversaries that actively manipulate input data to fool learning…
In this paper, we implement three state-of-art continuous reinforcement learning algorithms, Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Policy Gradient (PG)in portfolio management. All of them are…