MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck
cs.AI
Submitted: 2026-07-30
Updated: 2026-10-12
Terminology
Sources
- Detecting Language Model Attacks with Perplexity
- A Survey on Universal Approximation Theorems
- Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- The Llama 3 Herd of Models
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- LLMs Get Lost In Multi-Turn Conversation
- SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- GPT-4o System Card
- MemLineage: Lineage-Guided Enforcement for LLM Agent Memory
- MemGPT: Towards LLMs as Operating Systems
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
- Information bottleneck through variational glasses
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Agent Workflow Memory
- A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory
- The Rise and Potential of Large Language Model Based Agents: A Survey
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems