works on
defense mechanisms 1information bottleneck 1intent-aware detection 1LLM agents 1memory injection attacks 1

From the 1 of 1 linked paper with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck

Dongyi Liu, Haixing He, Xiaobao Wu +1

The paper introduces MIND, a lightweight framework that uses an intent‑aware information bottleneck to detect and filter poisoned memory in large language model agents, reducing at…