https://www.catalyzex.com/paper/a-practical-memory-injection-attack-against
A Practical Memory Injection Attack against LLM Agents
A Practical Memory Injection Attack against LLM Agents: Paper and Code. Agents based on large language models (LLMs) have demonstrated strong capabilities in a...
memory injectionllm agentspracticalattack
https://arxiv.org/abs/2602.15344
[2602.15344] ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented...
Abstract page for arXiv paper 2602.15344: ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models
black boxmemory injectionlong termmiaadversarial