Recent Papers / arXiv:2606.02240

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

arXiv:2606.02240Submitted Jun 3, 20260 benchmark results

Authors pending

View PDF ↗arXiv page ↗Edit
Abstract

215 indirect prompt injection scenarios across 24 enterprise integrations; guard model cuts attack success rate from 69.9% to 2.4%.

Tasks
edit
• Agentic AI
Results

No benchmark results recorded yet.

submit

Benchmark results referencing this paper haven't been added to the registry yet. If you have a reproduction, submit it →

CodeSOTA extraction

Benchmark evidence

edit
  • Extract AgentRedBench ASR per model and per attack type to confirm the 2.4% ASR with AgentRedGuard at 0.37% FPR.
Add or update benchmark results
Logged-in editor · benchmark trail
Read next

Three places to go from here.

Index
All papers
All tracked papers in the registry, with benchmark result, model, and leaderboard linkage where available.
Replacement
Papers with Code is dead — alternatives
What replaced PWC for each use case: LLMs, OCR, speech, vision, robotics.
Top hub
Agentic AI
Every benchmark in Agentic AI.