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