- Rating
- 3(+1)
- Confidence
- 2(−2)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes LCGuard to reduce sensitive information leakage through KV-cache sharing in multi-agent LLM systems. It learns residual transformations using an adversarial reconstruction objective while preserving downstream task utility. Experiments consider local and system-level adversary observations across multiple model families, privacy benchmarks, and communication topologies, reporting reduced attack success with relatively modest losses in task accuracy.
Critical strengths
The paper addresses a meaningful privacy risk in KV-based multi-agent communication, particularly leakage from aggregating multiple messages. This is a useful problem formulation beyond evaluating privacy only through final outputs.
The claimed results across several model families, benchmarks, and topologies suggest that learned KV transformations can reduce reconstruction success while retaining much of the task accuracy. If validated, this would offer a practical approach to protecting latent communication.
Critical weaknesses
It is unclear whether LCGuard removes sensitive information from the shared KV caches. The bottleneck only limits the residual update, while the original representation passes through an identity connection. Also, only final-layer KV caches are transformed, and the paper does not explain whether other layers are shared or protected.
Per-Agent and Full-System LCGuard use different privacy weights (\beta=0.25 and 0.5). It is therefore unclear whether Full-System’s lower attack success rate comes from its system-level design or the stronger privacy penalty.
Questions for authors
See the Critical Weaknesses.
4 comments
Dear Reviewer 3khJ,
Thank you again for your time and constructive feedback.
In our rebuttal, we have: (1) clarified the role of the residual bottleneck and the empirical nature of LCGuard's privacy protection; (2) clarified the scope of final-layer KV transformations and the corresponding protection boundary; and (3) provided additional matched-β comparisons between Per-Agent and Full-System LCGuard, directly addressing the concern that their performance differences may result from different privacy regularization strengths.
As the discussion period is approaching its end, we would greatly appreciate it if you could let us know whether any further questions or concerns remain. We would be happy to address them and would appreciate your reconsideration in light of the additional evidence.
Best regards,
Authors
Thank you for the explanations. Most of my previous concerns have been addressed. The results make sense to me and help me understand the position of the paper, and I therefore have decided to raise my rating. I wish the authors all the best with their work.
We sincerely thank the reviewer for their thoughtful reassessment, encouraging feedback, and decision to raise the rating. We greatly appreciate their time and constructive guidance.
Regards Authors
We thank the reviewer for the constructive feedback and address both concerns below.
W1: Residual Connection, Information Leakage, and KV-Layer Coverage
Residual connection. LCGuard applies learned residual transformations to the KV representations before transmission (Appendix A.6.1, Eqs. 21–25). Although the raw KV tensors are not transmitted separately, the identity pathway remains within the sanitized representations. We agree that the residual bottleneck does not guarantee information removal or irrecoverability; privacy protection arises from adversarially optimized transformations and is evaluated empirically through reconstruction attacks (Sec. 3.2).
For example, on Qwen3-4B sequential PrivacyLens (Table 1), Full-System LCGuard reduces ASR from 0.8676 (Vanilla KV) to 0.2191, while maintaining helpfulness of 0.7028. These results establish reduced recoverability against the evaluated adversary, rather than a formal information-theoretic privacy guarantee.
KV-layer coverage. Appendix A.6.1 specifies that the transformation operates on final-layer KV representations. We acknowledge that the current description does not sufficiently distinguish the transformed representation from the complete communicated KV artifact. We will explicitly document the transmitted layer indices, tensor contents, and receiver-side integration to clarify the protection boundary. In particular, any additional KV layers transmitted without sanitization would remain outside LCGuard's protection and constitute a separate leakage surface.
We will clarify that the bottleneck limits the capacity of the learned residual update, not the information content of the full transmitted representation, and state the precise scope of KV-layer protection.
W2: Privacy-Weight Confounding in Per-Agent vs. Full-System LCGuard
We agree that the original comparison uses different privacy weights: β=0.25 for Per-Agent and β=0.50 for Full-System LCGuard (Appendix A.6). These configurations were selected to balance privacy protection and task utility for their respective training objectives, rather than to isolate the effect of system-level optimization. Specifically, Per-Agent LCGuard optimizes reconstruction resistance from individual communication artifacts (Mobs={mij}), whereas Full-System LCGuard considers the joint collection of transmitted artifacts (Mobs=M). Since these objectives differ in adversarial observation scope, their privacy–utility operating points need not correspond to identical values of β.
Nevertheless, we acknowledge that the different privacy weights confound attribution of Full-System's improvement specifically to joint optimization.
Matched-β comparison. To isolate the contribution of optimization scope, both variants should be compared at β∈{0.25,0.50}, using identical backbones, data splits, communication topologies, and training budgets. Crucially, both guards must be evaluated using independently trained reconstruction adversaries with access to the same joint communication collection M, regardless of their training observation sets.
Table 1: Matched-β comparison of Per-Agent and Full-System LCGuard on Qwen3-4B, PrivacyLens, sequential topology (4 agents).
The results in (Table 1) show that Full-System LCGuard achieves ASR 0.2191, compared with 0.2661 for Per-Agent LCGuard, while maintaining higher helpfulness (0.7028 versus 0.6425). However, because these configurations use different privacy weights, the improvement cannot be attributed solely to joint reconstruction optimization.