ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems
cs.CR, cs.AI, cs.MA
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/SalesforceAIResearch/ErosionBench
Terminology
Sources
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- LlamaFirewall: An open source guardrail system for building secure AI agents
- BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
- MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models
- EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
- BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
- Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents
- AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox
- Progent: Securing AI Agents with Privilege Control
- CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity
- Multi-Agent Systems Execute Arbitrary Malicious Code
- MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems
- Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
- Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data