Related papers: Explainable Autonomous Cyber Defense using Adversa…

Algorithms that exploit factored Markov decision processes are far more sample-efficient than factor-agnostic methods, yet they assume a factored representation is known a priori -- a requirement that breaks down when the agent sees only…

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely…

Existing multi-agent path finding (MAPF) solvers do not account for uncertain behavior of uncontrollable agents. We present a novel variant of Enhanced Conflict-Based Search (ECBS), for both one-shot and lifelong MAPF in dynamic…

The path to higher network autonomy in 6G lies beyond the mere optimization of key performance indicators (KPIs), requiring systems that perceive and reason over the network environment as it is. This can be achieved through agentic AI,…

We consider a Markov decision process (MDP) in which actions prescribed by the controller are executed by a separate actuator, which may behave adversarially. At each time step, the controller selects and transmits an action to the…

As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations. We outline an approach to imitation learning for reverse-engineering black box…

Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules. The challenge lies in ensuring that the agent consistently adheres to these rules and policies,…

Fast and effective incident response is essential to prevent adversarial cyberattacks. Autonomous Cyber Defense (ACD) aims to automate incident response through Artificial Intelligence (AI) agents that plan and execute actions. Most ACD…

Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities. This sequential approach creates a mismatch --…

Over the years, most research towards defenses against adversarial attacks on machine learning models has been in the image recognition domain. The ML-based malware detection domain has received less attention despite its importance.…

Adversarial training (AT) is a widely recognized defense mechanism to gain the robustness of deep neural networks against adversarial attacks. It is built on min-max optimization (MMO), where the minimizer (i.e., defender) seeks a robust…

The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managing the vast influx of data from these platforms poses a…

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…

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Efficient communication can enhance the overall performance of collaborative multi-agent reinforcement learning. A common approach is to share observations through full communication, leading to significant communication overhead. Existing…

Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired target class. Existing methods face two key limitations: (1)…

While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversarial examples. Considering the safety critical applications…

In cooperative multi-agent reinforcement learning (c-MARL), agents learn to cooperatively take actions as a team to maximize a total team reward. We analyze the robustness of c-MARL to adversaries capable of attacking one of the agents on a…

Understanding the decision-making process of Deep Reinforcement Learning agents remains a key challenge for deploying these systems in safety-critical and multi-agent environments. While prior explainability methods like StateMask, have…