pith. sign in

34th USENIX Security Symposium (USENIX Security 25) , pages=

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.CR 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

How Adversarial Environments Mislead Agentic AI?

cs.AI · 2026-04-20 · unverdicted · novelty 6.0

Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.

citing papers explorer

Showing 2 of 2 citing papers.

  • Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation cs.CR · 2026-05-11 · unverdicted · none · ref 23

    M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.

  • How Adversarial Environments Mislead Agentic AI? cs.AI · 2026-04-20 · unverdicted · none · ref 3

    Adversarial compromise of tool outputs misleads agentic AI via breadth and depth attacks, revealing that epistemic and navigational robustness are distinct and often trade off against each other.