← Search

Thomas Hou

3 accepted papers

2026

Detecting Temporal Misalignment Attacks in Multimodal Fusion for Autonomous Driving

ICLR 2026poster

Multimodal fusion (MMF) is crucial for autonomous driving perception, combining camera and LiDAR streams for reliable scene understanding. However, its reliance on precise temporal synchronization introduces a vulnerability: adversaries can exploit network-induced delays to subtly misalign sensor st…

Cited by 0SourceScholar
2026

MINIM: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization

ICML 2026poster

Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the c…

Cited by 0SourceScholar
2026

Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning

ICML 2026poster

The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but also introduced new attack surfaces beyond prompt injection. In particular, cross-tool description poisoning can manipulate planner-visible tool metadata to steer an agent’s trajec…

Cited by 0SourceScholar