- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
Current backdoor defenses leave latent backdoor features in the sanitized models, which allows the reactivation of the backdoor. To achieve deep erasure of the backdoor, the authors propose GRAF (Gradient-Aligned Reactivation Forgetting) as a defense that introduces a small input-agnostic perturbation to simulate an adaptive reactivation attack. Learning to lower the error loss against this perturbation enables clean alignment and gradient-level erasing of the reactivation backdoor attack.
Critical strengths
- Defending the reactivation backdoor is crucial.
The targeted defense objective is crucial to truly removing the implanted backdoor. The latent reactivation attack requires deep sanitization.
- Comprehensive evaluation.
The authors provide extensive experiments across related defenses and the proposed work, offering a comprehensive evaluation and showing the advantage of GARF.
Critical weaknesses
- Mismatch between the threat model and the GA perturbation
According to the abstract and the threat model, the defender has no prior knowledge of any potential backdoor. However, the construction of GA perturbation uses the backdoor's target . This either violates the threat model, or the determination process of the backdoor's target is missing.
- The rationale of using the gradients for the similarity measurement.
Within in Eq(7), the second term measures the inner-product similarity between and . However, there is a lack of an interpretation of why can represent the gradient discrepancy .
- The objective loss function used in Eq(7) is missing.
The applied loss function for the perturbation generation is not introduced after Eq(7).
- Evaluation with entirely clean models is missing
As the threat model includes the situation where the defender may receive a clean, not backdoored model, the impact of using GARF is not investigated.
Questions for authors
See weaknesses above.