Showing 2026Show all
2 papers · 1 filter
cs.CR2026
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
Shanghao Shi, Xiao Wang, Chaoyu Zhang +6
The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but it also introduces new attack surfaces beyond prompt injecti…
cs.LG2026
Low Rank Adaptation for Adversarial Perturbation
Han Liu, Shanghao Shi, Yevgeniy Vorobeychik +2
Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large…