Related papers: Multi-Agent Systems Execute Arbitrary Malicious Co…

Cooperative information shared among a multi-agent system (MAS) can be useful to agents to efficiently fulfill their missions. Relying on wrong information, however, can have severe consequences. While classical approaches only consider…

We explore the use of GPT-4 on a humanoid robot in simulation and the real world as proof of concept of a novel large language model (LLM) driven behaviour method. LLMs have shown the ability to perform various tasks, including robotic…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

As Large Language Models (LLMs) have become integral to both research and daily operations, rigorous evaluation is crucial. This assessment is important not only for individual tasks but also for understanding their societal impact and…

LLM-based programming assistants offer the promise of programming faster but with the risk of introducing more security vulnerabilities. Prior work has studied how LLMs could be maliciously fine-tuned to suggest vulnerabilities more often.…

Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems,…

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and complexity. Large Language Models (LLMs) offer new opportunities for automating these tasks,…

The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited…

Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most…

Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…

Computer-aided teacher training is a state-of-the-art method designed to enhance teachers' professional skills effectively while minimising concerns related to costs, time constraints, and geographical limitations. We investigate the…

Large language model (LLM)-based multi-agent systems have demonstrated remarkable promise for tackling complex tasks by breaking them down into subtasks that are iteratively planned, executed, observed, and refined. Despite their…

In recent years, a significant research effort has been devoted to the design of distributed protocols for the control of multi-agent systems, as the scale and limited communication bandwidth characteristic of such systems render…

Effective collaboration in multi-agent systems requires communicating goals and intentions between agents. Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter-module communication,…

For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

The advancement of natural language processing (NLP) has been significantly boosted by the development of transformer-based large language models (LLMs). These models have revolutionized NLP tasks, particularly in code generation, aiding…

Stochastic multi-agent systems are a central modeling framework for autonomous controllers, communication protocols, and cyber-physical infrastructures. In many such systems, however, transition probabilities are only estimated from data…

The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderation systems rely on centralised, top-down rules, often…