2 citations · 3 across the 15 of their papers we have counts for
18 papers
How Much Do Activation Monitors Benefit from Original Model Computations?
James Oldfield, Shawn Im, Jay J Culligan +3
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and…
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield +5
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM…
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
Zihao Zhu, Siwei Lyu, Adel Bibi +1
A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a specif…
The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents
Baoyuan Wu, Qingshan Liu, Adel Bibi +2
This position paper argues that the Authorization-Execution Gap (AEG) is a major safety and security problem in open-world agents. The AEG is the divergence between what a principa…
Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode
Zeyuan He, Yupeng Chen, Lang Lin +7
Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefit…
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…
Reliable and Responsible Foundation Models: A Comprehensive Survey
Xinyu Yang, Junlin Han, Rishi Bommasani +49
Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), a…
The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
Yupeng Chen, Junchi Yu, Aoxi Liu +3
Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment ina…
Tahakom LLM Guidelines and Recipes: From Pre-training Data to an Arabic LLM
Areej AlOtaibi, Lina Alyahya, Raghad Alshabanah +12
Large Language Models (LLMs) have significantly advanced the field of natural language processing, enhancing capabilities in both language understanding and generation across diver…
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…
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…
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
James Oldfield, Philip Torr, Ioannis Patras +2
Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, traditional safety monitors often r…
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…
Mixture of Experts Made Intrinsically Interpretable
Xingyi Yang, Constantin Venhoff, Ashkan Khakzar +4
Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on pos…
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…
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions
Hazel Kim, Tom A. Lamb, Adel Bibi +2
Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, te…
Efficient Error Certification for Physics-Informed Neural Networks
Francisco Eiras, Adel Bibi, Rudy Bunel +3
Recent work provides promising evidence that Physics-Informed Neural Networks (PINN) can efficiently solve partial differential equations (PDE). However, previous works have failed…
Diversified Dynamic Routing for Vision Tasks
Botos Csaba, Adel Bibi, Yanwei Li +2
Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all s…