Papers › Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples

Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples

27 Oct 2018NeurIPS 2018 12arXiv:1810.11580archive 2025-07-28

Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang

Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either assume prior knowledge of specific attacks or may not work well on complex models due to their underlying assumptions. We argue that adversarial sample attacks are deeply entangled with interpretability of DNN models: while classification results on benign inputs can be reasoned based on the human perceptible features/attributes, results on adversarial samples can hardly be explained. Therefore, we propose a novel adversarial sample detection technique for face recognition models, based on interpretability. It features a novel bi-directional correspondence inference between attributes and internal neurons to identify neurons critical for individual attributes. The activation values of critical neurons are enhanced to amplify the reasoning part of the computation and the values of other neurons are weakened to suppress the uninterpretable part. The classification results after such transformation are compared with those of the original model to detect adversaries. Results show that our technique can achieve 94% detection accuracy for 7 different kinds of attacks with 9.91% false positives on benign inputs. In contrast, a state-of-the-art feature squeezing technique can only achieve 55% accuracy with 23.3% false positives.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 9 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

AmIAttribute/AmI officialmentioned in papermentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified 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

9 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran
1unverified

Licence: 0 of the 9 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 AmIAttribute/AmI. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

AmIAttribute/AmI official repository 9 samples, 8 ran (0 instrument-failed) · 1 unverified
get_data in 223 papers src/pytorch/utils.py ran MIT (permissive) · 527026ac594ba84c · report fixture: signature img_path:str/0/str, is_rgb:bool/0/bool · returned Tensor · level recorded 2026-09-25
get_identity src/utils.py ran MIT (permissive) · 5835046cc604e292 · report fixture: signature img_name:str/0/str, names:list/1/str · returned int · level recorded 2026-09-25
get_vgg_data src/utils.py ran MIT (permissive) · cbbda0f96bb49df7 · report fixture: signature img_path:str/0/str · returned ndarray · level recorded 2026-09-25
neuron_AmI src/pytorch/ami_model.py ran MIT (permissive) · a3583af3291bda9f · report fixture: signature x:Tensor/4/float, weaken_neurons:Tensor/1/float, strengthen_neurons:list/1/Tensor, attri_neurons:Tensor/1/int, layer_i:int/0/int, weaken_param:Tensor/0/float, strengthen_param0:Tensor/0/float, strengthen_param1:Tensor/0/float · returned Tensor · level recorded 2026-09-25
read_list in 14 papers src/utils.py ran MIT (permissive) · 2f2e5dd17df89181 · report fixture: signature f:str/0/str · returned list · level recorded 2026-09-25
strengthen src/pytorch/ami_model.py ran fingerprinted MIT (permissive) · ed7337b1847afb49 · report fixture: signature x:Tensor/2/float, strengthen_param0:Tensor/0/float, strengthen_param1:Tensor/0/float · returned Tensor · level recorded 2026-09-25
vgg_face_dag src/pytorch/vgg_face_dag.py ran MIT (permissive) · abe9c8d32f455980 · report fixture: signature weights_path:NoneType/0/? · returned Vgg_face_dag · level recorded 2026-09-25
weaken src/pytorch/ami_model.py ran fingerprinted MIT (permissive) · 9171c68c23bef65a · report fixture: signature x:Tensor/2/float, weaken_param:float/0/float · returned Tensor · level recorded 2026-09-25
get_vgg_data src/pytorch/utils.py unverified MIT (permissive) · af280a1f457a32e3 · report

Tasks

AttributeFace RecognitionGeneral Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Interpretability

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