EUVIMEDEUVIMED entdecken
Crossref

TWINFUZZ: Dual-Model Fuzzing for Robustness Generalization in Deep Learning

Enze Dai, Wentao Mo, Kun Hu, Xiaogang Zhu, Xi Xiao, Sheng Wen, Shaohua Wang, Yang Xiang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (44) · 37314-37322

DOI: 10.1609/aaai.v40i44.41063 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Enze Dai und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) models are increasingly deployed in safety-critical applications such as face recognition, autonomous driving, and medical diagnosis. Despite their impressive accuracy, they remain vulnerable to adversarial examples - subtle perturbations that can cause incorrect predictions, i.e., the robustness issues. While adversarial training improves robustness against known attacks, it often fails to generalize to unseen or stronger threats, revealing a critical gap in robustness generalization. In this work, we propose a dual-model fuzzing framework to enhance generalized robustness in DL models. Central to our method is a lightweight metric, the Lagrangian Information Bottleneck (LIB), which guides entropy-based mutation toward semantically meaningful and high-risk regions of the input space. The executor uses a resistant model and a more error-prone vulnerable model; their prediction consistency forms the basis of agreement mining, a label-free oracle for isolating decision-boundary samples. To ensure fuzzing effectiveness, we further introduce a task-driven seed selection strategy (e.g., SSIM for vision) that filters out low-quality inputs. We implement a prototype, TWINFUZZ, and evaluate it on six benchmark datasets and nine DL models. Compared with state-of-the-art testing approaches, TWINFUZZ achieves superior improvements in both training-specific and generalized robustness.

Zitieren

APA

Dai, E., Mo, W., Hu, K., Zhu, X., Xiao, X., Wen, S., Wang, S., & Xiang, Y. (2026). TWINFUZZ: Dual-Model Fuzzing for Robustness Generalization in Deep Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 37314-37322. https://doi.org/10.1609/aaai.v40i44.41063

Vancouver

Dai E, Mo W, Hu K, Zhu X, Xiao X, Wen S, et al. TWINFUZZ: Dual-Model Fuzzing for Robustness Generalization in Deep Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(44):37314-37322. doi:10.1609/aaai.v40i44.41063

BibTeX
@article{Dai2026,
  author = {Dai, Enze and Mo, Wentao and Hu, Kun and Zhu, Xiaogang and Xiao, Xi and Wen, Sheng and Wang, Shaohua and Xiang, Yang},
  title = {TWINFUZZ: Dual-Model Fuzzing for Robustness Generalization in Deep Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {44},
  pages = {37314--37322},
  doi = {10.1609/aaai.v40i44.41063}
}
Kostenlos starten →