No article text was recorded for this version.
persistent memory poisoning
Version 1 of 144 papers86 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Zombie Agents: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections
- Blog: Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
- Blog: From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
- Blog: Before It Persists: Write-Time Defense for Multimodal Agent Memory
- Blog: Memory Injection Attacks on LLM Agents via Query-Only Interaction
- Blog: A Survey on Trustworthy LLM Agents: Threats and Countermeasures
- Blog: AI Agents in Cryptoland: Practical Attacks and No Silver Bullet
- Blog: Get the Agents Drunk: Memory Perturbations in Autonomous Agent-based Recommender Systems
- Blog: Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
- Blog: A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
- Blog: MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
- Blog: Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
- Blog: VerificAgent: Integrating Expert Knowledge and Fact-Checked Memory for Robust Domain-Specific Task Planning
- Blog: A-MemGuard: A Proactive Defense Framework For LLM-Based Agent Memory
- Blog: From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
- Blog: More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models
- Blog: MemIncept: Steering LLM Agents via Cooperative Stealthy Memory Injections
- Blog: Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
- Blog: Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
- Blog: Sparse Adversarial Perturbations for Videos
- Blog: Artificial Immune System of Secure Face Recognition Against Adversarial Attacks
- Blog: CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
- Blog: AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
- Blog: NODLINK: An Online System for Fine-Grained APT Attack Detection and Investigation
- Blog: A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
- Blog: AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- Blog: The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
- Blog: Persistent Semantic Entities in Tool-Augmented LLM Systems
- Blog: TRAttack": " Text Rewriting Attack Against Text Retrieval
- Blog: Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
- Blog: Emerging Cyber Attack Risks of Medical AI Agents
- Blog: LLM Agents Should Employ Security Principles
- Blog: PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance
- Blog: RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
- Blog: Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents
- Blog: BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
- Blog: A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents
- Blog: Context manipulation attacks : Web agents are susceptible to corrupted memory
- Blog: Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
- Blog: DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
- Blog: AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
- Blog: From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions
- Blog: BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
- Blog: Learning and Unlearning of Fabricated Knowledge in Language Models
History & citation
Current · Permanent link
- This direction split from Securing Autonomous Agents Against Persistent Memory Poisoning (68% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_persistent_memory_poisoning_97a5ecb9,
title = {persistent memory poisoning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/persistent-memory-poisoning/rdr_97a5ecb94bc1446ab1f048bbdca12948},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_persistent_memory_poisoning_97a5ecb9_v1,
title = {persistent memory poisoning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/persistent-memory-poisoning/rdr_97a5ecb94bc1446ab1f048bbdca12948/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}