From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/openclaw/openclaw
Sources
- Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems
- Algorithmic Recourse: from Counterfactual Explanations to Interventions
- Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
- CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
- A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- MemGPT: Towards LLMs as Operating Systems
- Generative Agents: Interactive Simulacra of Human Behavior
- Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents
- Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
- SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
- MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
- Memory Poisoning Attack and Defense on Memory Based LLM-Agents
- MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
- Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR
- Voyager: An Open-Ended Embodied Agent with Large Language Models
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