Self-evolving LLM agents can be attacked by planting individually benign experiences that jointly weaken their safety boundaries.
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benign Alone, Harmful Together: Exploiting Experience Composition in Self-Evolving LLM Agents
Self-evolving LLM agents can be attacked by planting individually benign experiences that jointly weaken their safety boundaries.