- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes T-ISO for purifying backdoors embedded in model weights. Its distinctive design constructs two proxy models and identifies shared sensitive channels through parameter differencing and cross-proxy ranking, followed by channel zeroing and fine-tuning on benign responses to remove unknown backdoors. Experimental results demonstrate that the proposed T-ISO algorithm achieves strong backdoor defense performance.
Critical strengths
-
The manuscript presents a clear research motivation, and the proposed algorithm is novel.
-
The design of the proposed T-ISO algorithm is reasonable and theoretically grounded.
-
The experimental results demonstrate that T-ISO achieves strong defensive performance.
Critical weaknesses
-
The poisoning ratio of 50% used in the manuscript is excessively high. Although an ablation study on the poisoning ratio is provided, such a substantial level of poisoning may potentially affect the validity of the analysis.
-
The Triggered Branch of T-ISO is trained using 100% triggered samples, without any clean samples as a constraint. How can the authors ensure that the model has genuinely learned the backdoor trigger relationship, rather than simply tending to generate the target regardless of whether the trigger is present?
-
T-ISO assumes that different triggers may rely on a shared internal mechanism. However, the possibility that the proxy backdoor and the original backdoor operate through non-overlapping internal pathways requires further verification.
-
The authors should explicitly report the specific forms of the six proxy triggers.
-
The manuscript provides relatively comprehensive validation of target generalization, but the evaluation of trigger generalization, particularly generalization across different trigger mechanisms, remains insufficient.
-
The manuscript only compares proxy training time with Purify, without reporting the runtime, computational resource consumption, or related efficiency metrics for the other major baselines.
Questions for authors
Please refer to weaknesses.
Thank you to the authors for the detailed rebuttal and extensive additional experiments. I appreciate that the new controlled ablations provide stronger evidence for the independent contribution of target matching and channel selection, while the expanded utility and runtime evaluations substantially address my concerns regarding the effectiveness–cost trade-off. These results strengthen the empirical justification for T-ISO. However, some concerns remain, particularly the limited mechanistic understanding of why proxy-derived signatures generalize to unknown backdoors, and the absence of comprehensive adaptive-attack evaluations.
Overall, I acknowledge the substantial improvements made during the rebuttal. I therefore decide to maintain my score of 3 (since it is already positive) and encourage the AC to consider both the strengthened empirical evidence and the remaining limitations in the final decision.