- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents MemMorph, a memory-poisoning attack that persistently manipulates tool selection in LLM agents without modifying tool descriptions or model parameters. The proposed method combines potential-query modeling, structured memory initialization, and constrained optimization to improve the retrievability and effectiveness of poisoned memories. Experiments across three benchmarks and ten LLM backbones demonstrate strong attack success rates, transferability, and persistence under continued benign interactions.
Critical strengths
- The paper addresses a security problem in LLM agents. Investigating how poisoned long-term memories can influence future tool-selection decisions is relevant and practically meaningful.
- The separation between memory retrievability and downstream attack effectiveness provides a useful perspective on the attack construction process.
- The experiments cover multiple benchmarks and a diverse set of LLM backbones, including both open-source and proprietary models. The results demonstrate relatively consistent improvements over the evaluated baselines.
Critical weaknesses
- The main components of MemMorph build on existing techniques, including potential-query modeling, retrieval-oriented optimization, gradient-based token refinement, and shadow-model verification. The structured memory initialization also relies on relatively straightforward combinations of factual, episodic, and procedural records.
- Section 3.2 assumes that the attacker has access to the memory processor, retrieval encoder, and a shadow agent for estimating attack effectiveness. The attack construction also requires knowledge of the target scenario and the intended and hazardous tools.
- The evaluation covers nine manually selected scenarios, each with a predefined intended tool and hazardous alternative. Moreover, both the potential queries and evaluation requests are generated from the same scenario specifications. Although the evaluation queries are held out during optimization, they may still share substantial semantic characteristics with the generated training queries.
- Appendix C.1 explicitly states that the comparisons control the number of poisoned records rather than the computational budget. MemMorph uses multiple stages of candidate generation, gradient-based refinement, and shadow-agent verification, which may require considerably more computation or model queries than some baselines.
- The retrieval objective in Eq. (5) encourages alignment with an assigned query centroid relative to other centroids from the same scenario. However, actual memory retrieval depends on competition with the full collection of benign memories, which is not explicitly represented in this objective. It is therefore unclear why relative alignment among scenario-specific centroids should be an effective surrogate for retrieval ranking in a large memory store.
Questions for authors
- How would MemMorph perform when the attacker has no access to the target memory processor or retrieval encoder, and can only interact with the deployed agent through a limited number of black-box queries?
- Could the authors provide a more detailed comparison of the computational costs of MemMorph and the baselines, including the number of shadow-agent evaluations and optimization queries?