AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
The tested approach finds stronger attacks than evaluated baselines and shows some cross-task and cross-model transfer.
Verify byline in the original ↗PUBLICATION BYLINE
Indexed publications with this author name. Affiliation and author identity require publication-specific evidence.
The tested approach finds stronger attacks than evaluated baselines and shows some cross-task and cross-model transfer.
Verify byline in the original ↗