Papers
arxiv:2608.23471

InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

Published on Aug 24
Authors:
,
,
,
,
,
,
,

Abstract

InjecMEM introduces a single-interaction memory injection attack that uses optimized adversarial commands and topical anchors to manipulate retrieval and steer outputs in LLM agents.

Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-specified output. Guided by the retrieval-then-generate mechanism of memory systems, we craft the injection with a retriever-agnostic anchor and an adversarial command. The anchor contains high-recall topical cues so that downstream retrieval consistently associates the record with the target topic. The command is a short sequence optimized to remain effective under uncertain fused contexts, variable placements, and long prompts so that it reliably steers outputs once retrieved. We learn the command via gradient-based coordinate search, averaging over synthetic prompt templates and insertion positions, and extend it to joint optimization across backbones to study transfer. Evaluated across multiple memory systems and backbone models, InjecMEM achieves reliable topic-conditioned retrieval and targeted generation, remains effective under memory drift, and leaves non-target queries unaffected. Our results underscore the need to harden memory systems and provide a reproducible framework for studying agent memory.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.23471
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2608.23471 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2608.23471 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2608.23471 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.