13 papers
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…
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…
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…
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…
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…
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…