Papers › Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to...

Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations

9 Feb 2022CVPR 2023 1arXiv:2202.04235archive 2025-07-28

Lei Hsiung, Yun-Yun Tsai, Pin-Yu Chen, Tsung-Yi Ho

Model robustness against adversarial examples of single perturbation type such as the ℓₚ-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their composition remains largely unexplored. In this paper, we first propose a novel method for generating composite adversarial examples. Our method can find the optimal attack composition by utilizing component-wise projected gradient descent and automatic attack-order scheduling. We then propose generalized adversarial training (GAT) to extend model robustness from ℓₚ-ball to composite semantic perturbations, such as the combination of Hue, Saturation, Brightness, Contrast, and Rotation. Results obtained using ImageNet and CIFAR-10 datasets indicate that GAT can be robust not only to all the tested types of a single attack, but also to any combination of such attacks. GAT also outperforms baseline ℓ_∞-norm bounded adversarial training approaches by a significant margin.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

IBM/composite-adv officialmentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CARBEN: Composite Adversarial Robustness Benchmark (arXiv:2207.07797; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial RobustnessScheduling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GAT

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