Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via $\textit{In-the-wild}$ Cascading Flow Optimization

Yixiao Chen (Tsinghua University) · Shikun Sun (Tsinghua University) · Jianshu Li (National University of Singapore) · Ruoyu Li (Tiktok) · Zhe Li (Rochester Institute of Technology) · Junliang Xing (Tsinghua University)

adversarial attacksadversarial velocity functionadversarially trained modelsblack-box scenarioscascading distribution shift trainingdefense mechanismsdual-flow frameworkgenerative attacksgenerator-based attacksinstance-agnosticmodel capacity model robustnessmulti-target taskstransfer attackstransferability

Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks have excellent generalization and transferability due to their instance-agnostic nature. However, when training generators for multi-target tasks, the success rate of transfer attacks is relatively low due to the limitations of the model's capacity. To address these challenges, we propose a novel Dual-Flow framework for multi-target instance-agnostic adversarial attacks, utilizing Cascading Distribution Shift Training to develop an adversarial velocity function. Extensive experiments demonstrate that Dual-Flow significantly improves transferability over previous multi-target generative attacks. For example, it increases the success rate from Inception-v3 to ResNet-152 by 34.58%. Furthermore, our attack method shows substantially stronger robustness against defense mechanisms, such as adversarially trained models.