Related papers: The Agent Web Model -- Modelling web hacking for r…
This review paper takes a comprehensive look at malicious attacks against FL, categorizing them from new perspectives on attack origins and targets, and providing insights into their methodology and impact. In this survey, we focus on…
Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, such as malicious Web content, files, email attachments, and…
Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…
Model-Based Reinforcement Learning involves learning a \textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \textit{planner}. Much of the recent research along these lines presents a…
With the advancement of Large-Language Models (LLMs) and Large Vision-Language Models (LVMs), agents have shown significant capabilities in various tasks, such as data analysis, gaming, or code generation. Recently, there has been a surge…
Federated learning is a technique that allows multiple entities to collaboratively train models using their data without compromising data privacy. However, despite its advantages, federated learning can be susceptible to false data…
Modern threats have emerged from the prevalence of social networks. Hostile actors, such as extremist groups or foreign governments, utilize these networks to run propaganda campaigns with different aims. For extremists, these campaigns are…
Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…
Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon…
Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…
Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into…
Mixed cooperative-competitive control scenarios such as human-machine interaction with individual goals of the interacting partners are very challenging for reinforcement learning agents. In order to contribute towards intuitive…
Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade…
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…
Nowadays, model-free reinforcement learning algorithms have achieved remarkable performance on many decision making and control tasks, but high sample complexity and low sample efficiency still hinder the wide use of model-free…
Communication networks able to withstand hostile environments are critically important for disaster relief operations. In this paper, we consider a challenging scenario where drones have been compromised in the supply chain, during their…
Improvements in the area of large language models have shifted towards the construction of models capable of using external tools and interpreting their outputs. These so-called web agents have the ability to interact autonomously with the…
Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration. Moreover, markets are inherently a…
We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed…