arXiv (All)
open access
Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH
LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world. A key emerging threat is Decomposition Attacks \cite{glukhov2024breach, jones2024adversaries} in which a harmful task is broken into simpler, benign subtasks
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation#307063
- All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable ... Attacks#1198939
- MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures#1356147
- Constraint Decay: The Fragility of LLM Agents in Backend Code Generation#168374
- HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving#667903
Record · ID 1232770
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive