PRISM: Causal Counterfactual Minimization of Agent Tool Privileges via Information Bottleneck Role Induction
cs.CR, cs.AI, cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Terminology
Sources
- Defeating Prompt Injections by Design
- MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
- Progent: Securing AI Agents with Privilege Control
- The information bottleneck method
- Agent-SafetyBench: Evaluating the Safety of LLM 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