Related papers: Catch Me If You Can: Improving Adversaries in Cybe…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Reinforcement learning is a popular method of finding optimal solutions to complex problems. Algorithms like Q-learning excel at learning to solve stochastic problems without a model of their environment. However, they take longer to solve…

The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP task into an…

Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a…

The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts.…

The goal of this paper is to propose a new Q-learning algorithm with a dummy adversarial player, which is called dummy adversarial Q-learning (DAQ), that can effectively regulate the overestimation bias in standard Q-learning. With the…

Prompt quality plays a critical role in the performance of the Segment Anything Model (SAM), yet existing approaches often rely on heuristic or manually crafted prompts, limiting scalability and generalization. In this paper, we propose…

This paper presents an adversary detection mechanism and a resilient control framework for multi-agent systems under spatiotemporal constraints. Safety in multi-agent systems is typically addressed under the assumption that all agents…

Advances in reinforcement learning research have demonstrated the ways in which different agent-based models can learn how to optimally perform a task within a given environment. Reinforcement leaning solves unsupervised problems where…

In recent years machine learning algorithms, and more specifically deep learning algorithms, have been widely used in many fields, including cyber security. However, machine learning systems are vulnerable to adversarial attacks, and this…

Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to…

Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as spam email filtering, malware detection and fake image generation, where security methods…

This paper presents a proof-of concept study for demonstrating the viability of building collaboration among multiple agents through standard Q learning algorithm embedded in particle swarm optimisation. Collaboration is formulated to be…

In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks,…

Cybersecurity spans multiple interconnected domains, complicating the development of meaningful, labor-relevant benchmarks. Existing benchmarks assess isolated skills rather than integrated performance. We find that pre-trained knowledge of…

Large Language Models (LLMs) have gained widespread popularity across diverse domains involving text generation, summarization, and various natural language processing tasks. Despite their inherent limitations, LLM-based designs have shown…

Large language models (LLMs) are increasingly deployed as autonomous agents in offensive cybersecurity. In this paper, we reveal an interesting phenomenon: different agents exhibit distinct attack patterns. Specifically, each agent exhibits…

We consider the issue of strategic behaviour in various peer-assessment tasks, including peer grading of exams or homeworks and peer review in hiring or promotions. When a peer-assessment task is competitive (e.g., when students are graded…

Tennis strategy optimization is a challenging sequential decision-making problem involving hierarchical scoring, stochastic outcomes, long-horizon credit assignment, physical fatigue, and adaptation to opponent skill. I present a…

The optimistic nature of the Q-learning target leads to an overestimation bias, which is an inherent problem associated with standard $Q-$learning. Such a bias fails to account for the possibility of low returns, particularly in risky…