记忆隐私与安全

记忆投毒、数据外泄、选择性遗忘的隐私保护

共 21 篇论文，自动生成于 2026-05-13

论文列表

• "ADAM: A Systematic Data Extraction Attack on Agent Memory via Adaptive Querying" — arXiv:2604.09747
• "Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents" — arXiv:2605.08442
• "MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory" — arXiv:2605.03228
• "Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs" — arXiv:"2604.12616"
• "Memory Poisoning Attack and Defense on Memory Based LLM-Agents" — arXiv:2601.05504
• "Memory Poisoning and Secure Multi-Agent Systems" — arXiv:2603.20357
• "A Survey on the Security of Long-Term Memory in LLM Agents: Toward Mnemonic Sovereignty" — arXiv:"2604.16548"
• "MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents" — arXiv:"2605.09530"
• "MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents" — arXiv:2605.03482
• "Three Birds, One Stone: Solving the Communication-Memory-Privacy Trilemma in LLM Fine-tuning Over Wireless Networks with Zeroth-Air Optimization" — arXiv:2604.12401
• "How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants" — arXiv:2601.16621
• "Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents" — arXiv:2604.02623
• "Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGs" — arXiv:2605.05459
• "Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models" — arXiv:"2512.18035"
• "SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety" — arXiv:2605.05704
• "SuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoning" — arXiv:2603.02240
• "Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo" — arXiv:2604.11563
• "The Role of System 1 and System 2 Semantic Memory Structure in Human and LLM Biases" — arXiv:2604.12816
• "Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration" — arXiv:2605.01970
• "Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents" — arXiv:2604.20582
• "Visual Inception: Memory Poisoning Attacks on Vision-Language Models" — arXiv:2604.16966