PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 9, 20250 citationsOpen Access

Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictions

View Full Paper
QZQilin ZhouHWHaipeng WangZWZhengyuan Wei

Key Points

  • CostCert achieves a certified accuracy retention of up to 57.3% against adversarial attacks under specific conditions.
  • Existing methods struggle with pairwise comparisons in top-k settings, leading to inaccurate certifications.
  • CostCert uses a scalable voting mechanism to avoid combinatorial explosion in label comparisons.
  • This approach enhances the resilience of deep learning models against adversarial patch attacks effectively.

Abstract

Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the prediction of the sole true label of a certified sample. However, existing techniques, if applicable to top-k predictions, commonly conduct pairwise comparisons on those votes between labels, failing to certify the sole true label within the top k prediction labels precisely due to the inflation on the number of votes controlled by the attacker (i.e., attack budget); yet enumerating all combinations of vote allocation suffers from the combinatorial explosion problem. We propose CostCert, a novel, scalable, and precise voting-based certified recovery defender. CostCert verifies the true label of a sample within the top k predictions without pairwise comparisons and combinatorial explosion through a novel design: whether the attack budget on the sample is infeasible to cover the smallest total additional votes on top of the votes uncontrollable by the attacker to exclude the true labels from the top k prediction labels. Experiments show that CostCert significantly outperforms the current state-of-the-art defender PatchGuard, such as retaining up to 57.3% in certified accuracy when the patch size is 96, whereas PatchGuard has already dropped to zero.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zhou et al. (2025) studied this question.

synapsesocial.com/papers/68e70db790569dd607ee67achttps://doi.org/10.48550/arxiv.2507.23335
Ask AI
Helpful
Bookmark
Share
View Full Paper