EUVIMEDEUVIMED entdecken
Crossref

Improving Sustainability of Adversarial Examples in Class-Incremental Learning

Taifeng Liu, Xinjing Liu, Liangqiu Dong, Yang Liu, Yilong Yang, Zhuo Ma

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 7269-7277

DOI: 10.1609/aaai.v40i9.37664 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Taifeng Liu und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current adversarial examples (AEs) are typically designed for static models. However, with the wide application of Class-Incremental Learning (CIL), models are no longer static and need to be updated with new data distributed and labeled differently from the old ones. As a result, existing AEs often fail after CIL updates due to significant domain drift. In this paper, we propose SAE to enhance the sustainability of AEs against CIL. The core idea of SAE is to enhance the robustness of AE semantics against domain drift by making them more similar to the target class while distinguishing them from all other classes. Achieving this is challenging, as relying solely on the initial CIL model to optimize AE semantics often leads to overfitting. To resolve the problem, we propose a Semantic Correction Module. This module encourages the AE semantics to be generalized, based on a generative model capable of producing universal semantics. Additionally, it incorporates the CIL model to correct the optimization direction of the AE semantics, guiding them closer to the target class. To further reduce fluctuations in AE semantics, we propose a Filtering-and-Augmentation Module, which first identifies non-target examples with target-class semantics in the latent space and then augments them to foster more stable semantics. Comprehensive experiments demonstrate that SAE outperforms baselines by an average of 31.28% when updated with a 9-fold increase in the number of classes.

Zitieren

APA

Liu, T., Liu, X., Dong, L., Liu, Y., Yang, Y., & Ma, Z. (2026). Improving Sustainability of Adversarial Examples in Class-Incremental Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 7269-7277. https://doi.org/10.1609/aaai.v40i9.37664

Vancouver

Liu T, Liu X, Dong L, Liu Y, Yang Y, Ma Z. Improving Sustainability of Adversarial Examples in Class-Incremental Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):7269-7277. doi:10.1609/aaai.v40i9.37664

BibTeX
@article{Liu2026,
  author = {Liu, Taifeng and Liu, Xinjing and Dong, Liangqiu and Liu, Yang and Yang, Yilong and Ma, Zhuo},
  title = {Improving Sustainability of Adversarial Examples in Class-Incremental Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {9},
  pages = {7269--7277},
  doi = {10.1609/aaai.v40i9.37664}
}
Kostenlos starten →