Right Tool, Wrong Parameters: Defending LLM Agents Against Parameter Poisoning
cs.CR
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Meta-SecAlign: Training LLMs against Prompt Injection for Robust Agents
- Defeating Prompt Injections by Design
- WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
- The Llama 3 Herd of Models
- AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
- Defending Against Indirect Prompt Injection Attacks With Spotlighting
- GPT-4o System Card
- Progent: Securing AI Agents with Privilege Control
- PromptArmor: Simple yet Effective Prompt Injection Defenses
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems
- Qwen3 Technical Report
- ReAct: Synergizing Reasoning and Acting in Language Models
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI 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