most citedSemantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Adversarial Moral Stress Testing of Large Language Models

Saeid Jamshidi, Foutse Khomh, Arghavan Moradi Dakhel +3

Evaluating the ethical robustness of large language models (LLMs) deployed in software systems remains challenging, particularly under sustained adversarial user interaction. Exist…