Papers › PubDef: Defending Against Transfer Attacks From Public Models

PubDef: Defending Against Transfer Attacks From Public Models

26 Oct 2023arXiv:2310.17645archive 2025-07-28

Chawin Sitawarin, Jaewon Chang, David Huang, Wesson Altoyan, David Wagner

Adversarial attacks have been a looming and unaddressed threat in the industry. However, through a decade-long history of the robustness evaluation literature, we have learned that mounting a strong or optimal attack is challenging. It requires both machine learning and domain expertise. In other words, the white-box threat model, religiously assumed by a large majority of the past literature, is unrealistic. In this paper, we propose a new practical threat model where the adversary relies on transfer attacks through publicly available surrogate models. We argue that this setting will become the most prevalent for security-sensitive applications in the future. We evaluate the transfer attacks in this setting and propose a specialized defense method based on a game-theoretic perspective. The defenses are evaluated under 24 public models and 11 attack algorithms across three datasets (CIFAR-10, CIFAR-100, and ImageNet). Under this threat model, our defense, PubDef, outperforms the state-of-the-art white-box adversarial training by a large margin with almost no loss in the normal accuracy. For instance, on ImageNet, our defense achieves 62% accuracy under the strongest transfer attack vs only 36% of the best adversarially trained model. Its accuracy when not under attack is only 2% lower than that of an undefended model (78% vs 80%). We release our code at https://github.com/wagner-group/pubdef.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.17645")

Code

Syntology Ran 10 of 12 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: found in paper text by Syntology: 12 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wagner-group/pubdef mentioned in papermentioned on GitHubjaxMIT 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.

Code Syntology ran Syntology

12 samples harvested; 10 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
8ran
2unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ZhengyuZhao/TransferAttackEval. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

TI_multi ZhengyuZhao/TransferAttackEval/attacks/input_augmentation_attacks.py found in paper text by Syntology ran no licence file found · pointer only · 54085cfa802ab165 · report
accuracy ZhengyuZhao/TransferAttackEval/attacks/utils_data.py found in paper text by Syntology ran no licence file found · pointer only · 713cbb90b09f2f2d · report
avg ZhengyuZhao/TransferAttackEval/attacks/feature_disruption_attacks.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · 7a1a277b5455acbd · report
backward_hook ZhengyuZhao/TransferAttackEval/attacks/surrogate_refinement_attacks.py found in paper text by Syntology ran no licence file found · pointer only · c753988805f48831 · report
backward_hook_norm ZhengyuZhao/TransferAttackEval/attacks/surrogate_refinement_attacks.py found in paper text by Syntology ran no licence file found · pointer only · 411972c3dc337b0d · report
conv1x1 ZhengyuZhao/TransferAttackEval/attacks/utils_iaa.py found in paper text by Syntology ran · our draft was wrong no licence file found · pointer only · 2a80220dabcb742a · report
conv3x3 ZhengyuZhao/TransferAttackEval/attacks/utils_iaa.py found in paper text by Syntology ran · our draft was wrong no licence file found · pointer only · 600ff2c45e0de056 · report
gkern ZhengyuZhao/TransferAttackEval/attacks/input_augmentation_attacks.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · c7faa7d1457e3557 · report
linbp_forw_resnet50 ZhengyuZhao/TransferAttackEval/attacks/surrogate_refinement_attacks.py found in paper text by Syntology ran no licence file found · pointer only · 20790bad3577ddcb · report
sow_images ZhengyuZhao/TransferAttackEval/attacks/feature_disruption_attacks.py found in paper text by Syntology ran no licence file found · pointer only · 6dd3f399496d6497 · report
TI ZhengyuZhao/TransferAttackEval/attacks/input_augmentation_attacks.py found in paper text by Syntology unverified no licence file found · pointer only · 7ce71b5da4faa32b · report
resnet50 ZhengyuZhao/TransferAttackEval/attacks/utils_iaa.py found in paper text by Syntology unverified no licence file found · pointer only · bfc5e139026a885d · report

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