提出双流框架，提升多目标攻击在真实场景下的迁移能力
Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization
- 通过级联分布偏移训练构建可迁移的对抗速度函数
- 在Inception-v3到ResNet-152上成功率提升34.58%
- 对防御模型有更强鲁棒性，适合评估模型安全性
对抗攻击广泛用于评估模型鲁棒性，在黑盒场景下，攻击的迁移能力至关重要。现有基于生成器的攻击因实例无关特性具有良好的泛化与迁移能力，但在训练多目标生成器时，受限于模型容量，迁移攻击成功率较低。为此，我们提出一种新型双流框架，用于多目标、实例无关的对抗攻击，采用级联分布偏移训练方法构建对抗速度函数。大量实验表明，该方法显著提升了先前多目标生成式攻击的迁移能力。例如，从Inception-v3到ResNet-152的成功率提升34.58%。此外，该攻击方法对防御机制（如对抗训练模型）表现出更强的鲁棒性。Dual-Flow代码已公开于：https://github.com/Chyxx/Dual-Flow。
原文摘要 · Abstract (English)
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. The code of Dual-Flow is available at: $\href{https://github.com/Chyxx/Dual-Flow}{https://github.com/Chyxx/Dual-Flow}$.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。