Papers › CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

30 Oct 2024arXiv:2410.23091archive 2025-07-28

Mingkun Zhang, Keping Bi, Wei Chen, Quanrun Chen, Jiafeng Guo, Xueqi Cheng

Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://github.com/CAS-AISafetyBasicResearchGroup/CausalDiff.

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="2410.23091")

Code

Syntology Ran 3 of 17 code samples harvested from 2 repositories linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 2 ran; found in paper text by Syntology: 13 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cas-aisafetybasicresearchgroup/causaldiff 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

17 samples harvested; 3 ran; 0 honoured the contract we drafted; 14 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.

1ran · fixture could not drive it
2ran
14unverified

Licence: 0 of the 17 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

BasicBlock cas-aisafetybasicresearchgroup/causaldiff/model/unet_autoenc.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · f847a1b1c3b13042 · report
Flatten cas-aisafetybasicresearchgroup/causaldiff/model/unet_autoenc.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 8990ccc3a7ed53f8 · report
NetworkBlock cas-aisafetybasicresearchgroup/causaldiff/model/unet_autoenc.py official repository unverified MIT (permissive) · 7e8b3a3ffd864e29 · report
d_LaCIM cas-aisafetybasicresearchgroup/causaldiff/model/unet_autoenc.py official repository unverified MIT (permissive) · 2b8bea10ddab8540 · report
space_timesteps tmlresearchgroup-cas/causaldiff/diffusion/diffusion.py found in paper text by Syntology ran · fixture could not drive it MIT (permissive) · 39352f70cb57396e · report
apply_conditions TMLResearchGroup-CAS/CausalDiff/model/blocks.py found in paper text by Syntology unverified MIT (permissive) · a14e237c2789b10d · report
chunk_size TMLResearchGroup-CAS/CausalDiff/dist_utils.py found in paper text by Syntology unverified MIT (permissive) · 235265a7a3a652fb · report
compute_acc tmlresearchgroup-cas/causaldiff/run_eval.py found in paper text by Syntology unverified MIT (permissive) · 3f55f85544860186 · report
compute_acc TMLResearchGroup-CAS/CausalDiff/experiment.py found in paper text by Syntology unverified MIT (permissive) · dd8d3dcf271eb1a8 · report
convert TMLResearchGroup-CAS/CausalDiff/lmdb_writer.py found in paper text by Syntology unverified MIT (permissive) · 6b0fadb6db123712 · report
is_time TMLResearchGroup-CAS/CausalDiff/experiment.py found in paper text by Syntology unverified MIT (permissive) · 4f9b67ed1294c6a0 · report
jsonable TMLResearchGroup-CAS/CausalDiff/config_base.py found in paper text by Syntology unverified MIT (permissive) · 3436fefeb3a4b49a · report
make_transform TMLResearchGroup-CAS/CausalDiff/dataset.py found in paper text by Syntology unverified MIT (permissive) · 7b0f30c49d628c72 · report
mean_nll tmlresearchgroup-cas/causaldiff/run_eval.py found in paper text by Syntology unverified MIT (permissive) · 9f4bd412a84d05e0 · report
psnr TMLResearchGroup-CAS/CausalDiff/metrics.py found in paper text by Syntology unverified MIT (permissive) · 79dd7b45925d286c · report
t_sample tmlresearchgroup-cas/causaldiff/run_eval.py found in paper text by Syntology unverified MIT (permissive) · c921df1a998cbb0f · report
use_cached_dataset_path TMLResearchGroup-CAS/CausalDiff/dataset_util.py found in paper text by Syntology unverified MIT (permissive) · 96226a66ab62eb91 · report

Tasks

Adversarial DefenseDisentanglementTraffic Sign Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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