StateFence: Task-State Protection Against Evidence-Chain Contamination in Blue-Team LLM Agents
cs.CR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
- CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning
- PIArena: A Platform for Prompt Injection Evaluation
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- CSLE: A Reinforcement Learning Platform for Autonomous Security Management
- AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
- AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
- MemGPT: Towards LLMs as Operating Systems
- Ignore Previous Prompt: Attack Techniques For Language Models
- PromptArmor: Simple yet Effective Prompt Injection Defenses
- LogJack: Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Defending Against Prompt Injection with DataFilter
- LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
- AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
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