PGA：面向实用无盒场景的无先验生成式攻击
PGA: Prior-free Generative Attack for Practical No-box Scenario
为视觉模型安全评估提供了一条无需先验数据、仅用少量无标签图像即可训练生成器产出对抗扰动的路径，其课程引导的微鲁棒优化与区域一致性扰动学习可直接迁移到黑盒迁移攻击与对抗训练的数据高效设定中。
原文依据 we propose Prior-free Generative Attack (PGA), the first generative attack tailored for the PNS
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论传统迁移攻击对大量先验信息的不切实际依赖催生了实用无盒场景（PNS），在该场景中攻击者只能访问少量无标签图像。然而，现有方法依赖迭代优化来生成对抗样本，其推理速度和迁移性本质上受限。相反，更快的生成式攻击由于严重依赖大量先验信息，而这类信息在该场景中明确缺失，因而与 PNS 存在根本冲突。为弥合这一差距，我们提出无先验生成式攻击（PGA），这是首个为 PNS 量身定制的生成式攻击。具体而言，我们引入课程引导的微鲁棒优化，逐步纳入更具挑战性的判别任务，以缓解有限数据下自监督学习常见的退化解问题，从而为下游攻击产出鲁棒且可迁移的代理模型。此外，区域感知一致性扰动学习引导生成器产生细粒度且空间连贯的扰动，缓解生成式攻击在监督不足时陷入局部最优的常见缺陷。大量实验表明，PGA 在多种设定下以高推理速度实现了显著的迁移性。本工作为未来迁移攻击研究提供了更实用的基准，揭示了生成式攻击在 PNS 下的巨大潜力。
英文原文摘要 1497 字符
The unrealistic reliance on abundant prior information in traditional transferable attacks has spurred the Practical No-box Scenario (PNS), where attackers can access only limited unlabeled images. However, existing methods rely on iterative optimization to produce adversarial examples with inherently limited inference speed and transferability. Conversely, faster generative attacks fundamentally conflict with the PNS due to their critical dependence on abundant prior information that is explicitly absent in this scenario. To bridge this gap, we propose Prior-free Generative Attack (PGA), the first generative attack tailored for the PNS. Specifically, we introduce the Curriculum-Guided Micro-Robust Optimization that progressively incorporates more challenging discriminative tasks to mitigate the degenerate solutions common in self-supervised learning with limited data, yielding robust and transferable surrogates for downstream attacks. Furthermore, the Region-Aware Consistent Perturbation Learning guides the generator to produce fine-grained and spatially coherent perturbations, mitigating the common pitfall of generative attacks falling into local optima under insufficient supervision. Extensive experiments demonstrate that our PGA achieves remarkable transferability across various settings with high inference speed. This work provides a more practical benchmark for future research on transferable attacks, revealing the great potential of generative attacks under the PNS.