- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposed ConCam, a targeted backdoor attack combining anchor consensus and camouflaged backdoor injection. Multiple target-class anchors are aggregated via consensus voting to get a reliable target-set construction. Sample-specific implicit triggers and dynamic poisoning selection are done for enabling backdoor at a very low injection ratio. The proposed attack is proven effective experimentally even under some VFL defenses for backdoor attacks.
Critical strengths
- According to the reported results, ConCam has a strong effectiveness–accuracy trade-off. Especially in the the low-budget comparison, with only per-batch poisoning rate, ConCam reports ASR which is amazing, comparing with others.
- The empirical results well supported the motivation of using multiple anchors with anchor-consensus to improve performance by reducing anchor sample selection sensitivity.
- Multiple aspects of the attack are reported alongside ASR, including target-set purity and perceptual distortion.
Critical weaknesses
- I suggest adding some visualization results to the main paper, which tells the story and demonstrates the result of the method better than using cold, pale narration and numerical results.
- The experiments are mainly done under setting with VFL parties, the active party and the malicious (passive party). What would be the case if more parties are involved in the VFL system? What if only one of the passive parties is malicious who has to rely on its own data for attack? And what if multiple passive parties collaborate to the same attack (they share the same attacking goal)? And what if multiple passive parties each has its own malicious attacking goal? I would like to see more results on these diverse settings.
- Another concern to me is that, if I understand correctly, the poisoning rate is defined as "per epoch". However, the selected poisoning positions can change. Therefore, with the accumulation across multiple epochs, the total number of samples modified or injected with triggers can grow linearly to a significantly larger number. The actual cumulative number could be smaller, but it is not reported. Comparisons should match cumulative modifications, distinct modified records, and training duration (number of training iterations or epochs) in addition to the per-epoch rate.
Questions for authors
- I would suggest adding besides the name of different evaluated statistics to give readers a direct sense of whether higher or lower values is better.