Papers › Transferability Bound Theory: Exploring Relationship between Adversarial...

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness

10 Nov 2023arXiv:2311.06423archive 2025-07-28

Mingyuan Fan, Xiaodan Li, Cen Chen, Wenmeng Zhou, Yaliang Li

A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its variants. However, the theoretical relationship between the transferability of adversarial examples and their flatness has not been well established, making the belief questionable. To bridge this gap, we embark on a theoretical investigation and, for the first time, derive a theoretical bound for the transferability of adversarial examples with few practical assumptions. Our analysis challenges this belief by demonstrating that the increased flatness of adversarial examples does not necessarily guarantee improved transferability. Moreover, building upon the theoretical analysis, we propose TPA, a Theoretically Provable Attack that optimizes a surrogate of the derived bound to craft adversarial examples. Extensive experiments across widely used benchmark datasets and various real-world applications show that TPA can craft more transferable adversarial examples compared to state-of-the-art baselines. We hope that these results can recalibrate preconceived impressions within the community and facilitate the development of stronger adversarial attack and defense mechanisms. The source codes are available in <https://github.com/fmy266/TPA>.

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="2311.06423")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

fmy266/tpa officialmentioned in papermentioned on GitHubpytorch 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; 8 ran; 0 honoured the contract we drafted; 4 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
2ran · fixture could not drive it
4ran
4unverified

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 fmy266/tpa. “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.

BaseAttack fmy266/tpa/toolkit/adv/attack.py official repository ran no licence file found · pointer only · 6fbe88d522599801 · report
TAEFEP fmy266/tpa/toolkit/adv/attack.py official repository ran no licence file found · pointer only · 6c7dce372a94f4eb · report
accuracy fmy266/tpa/FAA/acc_validate.py official repository ran · fixture could not drive it no licence file found · pointer only · fd638ce21929b00d · report
conv1x1 fmy266/TPA/FAA/resnet.py official repository ran · our draft was wrong no licence file found · pointer only · 2a80220dabcb742a · report
conv3x3 fmy266/TPA/FAA/resnet.py official repository ran · our draft was wrong no licence file found · pointer only · 600ff2c45e0de056 · report
densenet121 fmy266/TPA/FAA/densenet.py official repository ran no licence file found · pointer only · ad370ce5d85797b6 · report
resnet18 fmy266/TPA/FAA/resnet.py official repository ran no licence file found · pointer only · 864a6cf3c90af3e5 · report
unnormalize fmy266/tpa/FAA/acc_validate.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 90b8bf86c8334fb7 · report
clip_based_on_inf_norm_ fmy266/tpa/toolkit/adv/attack.py official repository unverified no licence file found · pointer only · 2e5c4fc85c6ed610 · report
densenet161 fmy266/TPA/FAA/densenet.py official repository unverified no licence file found · pointer only · 4db35ea5c8cdf3e0 · report
densenet169 fmy266/TPA/FAA/densenet.py official repository unverified no licence file found · pointer only · c200a9855de96b29 · report
validate fmy266/TPA/FAA/acc_validate.py official repository unverified no licence file found · pointer only · 0936271379c79ffa · report

Tasks

Adversarial AttackDiversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Sharpness-Aware Minimization

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