The paper proposes a bottom-up framework for safe agentic AI systems that treats each component as a dual-use interface where added capabilities also expand attack surfaces across single agents, multi-agent systems, and interoperable ecosystems.
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward a Safe Internet of Agents
The paper proposes a bottom-up framework for safe agentic AI systems that treats each component as a dual-use interface where added capabilities also expand attack surfaces across single agents, multi-agent systems, and interoperable ecosystems.