Papers › Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

7 Mar 2023arXiv:2303.03680archive 2025-07-28

Juanjuan Weng, Zhiming Luo, Zhun Zhong, Shaozi Li, Nicu Sebe

Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted adversarial examples with higher transferability than non-targeted ones. Recent studies reveal that the traditional Cross-Entropy (CE) loss function is insufficient to learn transferable targeted adversarial examples due to the issue of vanishing gradient. In this work, we provide a comprehensive investigation of the CE loss function and find that the logit margin between the targeted and untargeted classes will quickly obtain saturation in CE, which largely limits the transferability. Therefore, in this paper, we devote to the goal of continually increasing the logit margin along the optimization to deal with the saturation issue and propose two simple and effective logit calibration methods, which are achieved by downscaling the logits with a temperature factor and an adaptive margin, respectively. Both of them can effectively encourage optimization to produce a larger logit margin and lead to higher transferability. Besides, we show that minimizing the cosine distance between the adversarial examples and the classifier weights of the target class can further improve the transferability, which is benefited from downscaling logits via L2-normalization. Experiments conducted on the ImageNet dataset validate the effectiveness of the proposed methods, which outperform the state-of-the-art methods in black-box targeted attacks. The source code is available at Link (https://github.com/WJJLL/Target-Attack/)

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

wjjll/target-attack officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Success and Simplicity: A Second Look at Transferable Targeted Attacks (arXiv:2012.11207; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Trustworthy-AI-Group/TransferAttack mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets (arXiv:2002.05990; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified), Admix: Enhancing the Transferability of Adversarial Attacks (arXiv:2102.00436; that paper's own run record: 0 ran · 1 unverified), Enhancing the Transferability of Adversarial Attacks through Variance Tuning (arXiv:2103.15571; that paper's own run record: 0 ran · 1 unverified) and 10 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial Attack

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections