pith. machine review for the scientific record. sign in

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 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Toward a Safe Internet of Agents

cs.MA · 2025-11-29 · unverdicted · novelty 4.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Toward a Safe Internet of Agents cs.MA · 2025-11-29 · unverdicted · none · ref 29

    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.