Papers › Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes

26 Oct 2021NeurIPS 2021 12arXiv:2110.13541archive 2025-07-28

Sanghyun Hong, Michael-Andrei Panaitescu-Liess, Yiğitcan Kaya, Tudor Dumitraş

Quantization is a popular technique that transforms the parameter representation of a neural network from floating-point numbers into lower-precision ones (e.g., 8-bit integers). It reduces the memory footprint and the computational cost at inference, facilitating the deployment of resource-hungry models. However, the parameter perturbations caused by this transformation result in behavioral disparities between the model before and after quantization. For example, a quantized model can misclassify some test-time samples that are otherwise classified correctly. It is not known whether such differences lead to a new security vulnerability. We hypothesize that an adversary may control this disparity to introduce specific behaviors that activate upon quantization. To study this hypothesis, we weaponize quantization-aware training and propose a new training framework to implement adversarial quantization outcomes. Following this framework, we present three attacks we carry out with quantization: (i) an indiscriminate attack for significant accuracy loss; (ii) a targeted attack against specific samples; and (iii) a backdoor attack for controlling the model with an input trigger. We further show that a single compromised model defeats multiple quantization schemes, including robust quantization techniques. Moreover, in a federated learning scenario, we demonstrate that a set of malicious participants who conspire can inject our quantization-activated backdoor. Lastly, we discuss potential counter-measures and show that only re-training consistently removes the attack artifacts. Our code is available at https://github.com/Secure-AI-Systems-Group/Qu-ANTI-zation

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 10 ran (10 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

secure-ai-systems-group/qu-anti-zation officialmentioned in paperpytorchMITSyntology: 12 samples, 10 ran (0 instrument-failed) · 2 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

12 samples harvested: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. “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.

10ran
2unverified

Licence: 0 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 secure-ai-systems-group/qu-anti-zation. “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”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

secure-ai-systems-group/qu-anti-zation official repository 12 samples, 10 ran (0 instrument-failed) · 2 unverified
AsymmetricQuantizer attack_w_lossfn.py ran fingerprinted MIT (permissive) · 9a335d5e444ef7f6 · report fixture: returned AsymmetricQuantizer · level recorded 2026-09-22
MovingAverageRangeTracker attack_w_lossfn.py ran MIT (permissive) · 48c45d01e5c1b780 · report fixture: returned MovingAverageRangeTracker · level recorded 2026-09-22
QuantizedConv2d attack_w_lossfn.py ran fingerprinted MIT (permissive) · b37124bb0e393e91 · report fixture: returned QuantizedConv2d · level recorded 2026-09-22
QuantizedLinear attack_w_lossfn.py ran MIT (permissive) · d8db79419e17e540 · report fixture: returned QuantizedLinear · level recorded 2026-09-22
Quantizer in 10 papers attack_w_lossfn.py ran MIT (permissive) · d70c915efcf4d1a4 · report fixture: returned Quantizer · level recorded 2026-09-22
RangeTracker attack_w_lossfn.py ran MIT (permissive) · 04d0d5fd405c1f27 · report fixture: returned RangeTracker · level recorded 2026-09-22
Round attack_w_lossfn.py ran MIT (permissive) · 9c001f882200270e · report fixture: returned Round · level recorded 2026-09-22
SignedQuantizer attack_w_lossfn.py ran MIT (permissive) · 016074abfad976a6 · report fixture: returned SignedQuantizer · level recorded 2026-09-22
SymmetricQuantizer attack_w_lossfn.py ran fingerprinted MIT (permissive) · 8a74c2894fe32bb3 · report fixture: returned SymmetricQuantizer · level recorded 2026-09-22
UnsignedQuantizer attack_w_lossfn.py ran MIT (permissive) · cc8c55399eb7d028 · report fixture: returned UnsignedQuantizer · level recorded 2026-09-22
QuantizationEnabler attack_w_lossfn.py unverified MIT (permissive) · 19b7026f240ed406 · report
train_w_perturb attack_w_lossfn.py unverified MIT (permissive) · 8cff3673daceae2c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Qu-ANTI-zation (graph method: Qu-ANTI-zation). 12 bricks; individually on a fixture: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. train_w_perturb entry · level 0 · unverified · 8cff3673daceae2c
  2. QuantizationEnabler helper · level 0 · unverified · 19b7026f240ed406
  3. QuantizedConv2d helper · level 1 · ran · b37124bb0e393e91
  4. QuantizedLinear helper · level 1 · ran · d8db79419e17e540
  5. AsymmetricQuantizer helper · level 1 · ran · 9a335d5e444ef7f6
  6. MovingAverageRangeTracker helper · level 1 · ran · 48c45d01e5c1b780
  7. SymmetricQuantizer helper · level 1 · ran · 8a74c2894fe32bb3
  8. UnsignedQuantizer helper · level 1 · ran · cc8c55399eb7d028
  9. RangeTracker helper · level 1 · ran · 04d0d5fd405c1f27
  10. SignedQuantizer helper · level 1 · ran · 016074abfad976a6
  11. Quantizer helper · level 1 · ran · d70c915efcf4d1a4
  12. Round helper · level 1 · ran · 9c001f882200270e

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2110.13541") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Backdoor AttackFederated LearningQuantization

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