Steal Now and Attack Later：评估目标检测对黑盒对抗攻击的鲁棒性
Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
AI总结：
本研究提出基于“steal now, decrypt later”的黑盒对抗攻击方法，通过生成ghost objects增加目标检测推理延迟，在无目标模型先验知识下成功攻击多种模型与Google Vision API，单次成本低于1美元，揭示AI安全风险。
摘要：
针对目标检测的延迟攻击是对抗攻击的一种变体，旨在通过在目标图像中生成额外的ghost objects来增加推理时间。然而，在黑盒场景下生成ghost objects仍然是一个挑战，因为关于这些不合格对象的信息是不透明的。在本研究中，我们展示了通过扩展“steal now, decrypt later”攻击的概念，在对抗样本中生成ghost objects的可行性。这些对抗样本一旦生成，便可被用于利用AI服务中的潜在漏洞，引发严重的安全担忧。实验结果表明，所提出的攻击在多种常用模型和Google Vision API上均实现了成功攻击，且无需任何关于目标模型的先验知识。此外，每次攻击的平均成本低于1美元，对AI安全构成了重大威胁。
英文摘要：
Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image. However, generating ghost objects in the black-box scenario remains a challenge since information about these unqualified objects remains opaque. In this study, we demonstrate the feasibility of generating ghost objects in adversarial examples by extending the concept of "steal now, decrypt later" attacks. These adversarial examples, once produced, can be employed to exploit potential vulnerabilities in the AI service, giving rise to significant security concerns. The experimental results demonstrate that the proposed attack achieves successful attacks across various commonly used models and Google Vision API without any prior knowledge about the target model. Additionally, the average cost of each attack is less than \$ 1 dollars, posing a significant threat to AI security.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
