collaborators

7 papers

cs.AI2026

BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models

Thierry Blankenstein, Jialin Yu, Zixuan Li +6

Agents backed by large language models (LLMs) increasingly rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options. This raise…

cs.LG2026

FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction

Runqi Lin, Alasdair Paren, Suqin Yuan +4

The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual…

cs.AI2026

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

Akshat Naik, Jay Culligan, Yarin Gal +4

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has…

cs.CR2026

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

Lukas Aichberger, Alasdair Paren, Guohao Li +3

Recent advances in operating system (OS) agents have enabled vision-language models (VLMs) to directly control a user's computer. Unlike conventional VLMs that passively output tex…

cs.CR2025

ToolTweak: An Attack on Tool Selection in LLM-based Agents

Jonathan Sneh, Ruomei Yan, Jialin Yu +6

As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tool…

cs.LG2025

Focus On This, Not That! Steering LLMs with Adaptive Feature Specification

Tom A. Lamb, Adam Davies, Alasdair Paren +2

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and…