Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security concerns for real-world DNNs applications. Nevertheless, existing works mostly focus on investigating the adversarial transferability across different deep models that share the same modality of input data. The cross-modal transferability of adversarial perturbation has never been explored. This paper investigates the transferability of adversarial perturbation across different modalities, i.e., leveraging adversarial perturbation generated on white-box image models to attack black-box video models. Specifically, motivated by the observation that the low-level feature space between images and video frames are similar, we propose a simple yet effective cross-modal attack method, named as Image To Video (I2V) attack. I2V generates adversarial frames by minimizing the cosine similarity between features of pre-trained image models from adversarial and benign examples, then combines the generated adversarial frames to perform black-box attacks on video recognition models. Extensive experiments demonstrate that I2V can achieve high attack success rates on different black-box video recognition models. On Kinetics-400 and UCF-101, I2V achieves an average attack success rate of 77.88% and 65.68%, respectively, which sheds light on the feasibility of cross-modal adversarial attacks.
翻译:最近的研究显示,在一个白色框模型上手工制作的对抗性例子可以用来攻击其他黑盒模型。这种跨模版的可移动性使得可以进行黑盒攻击,这引起了对真实世界 DNNS 应用程序的安全关切。然而,现有的工作主要侧重于调查不同深度模型的对抗性转移性,这些模型具有相同的输入数据模式。对抗性扰动的交叉转移性从未被探索过。本文调查了不同模式,即利用白盒图像模型产生的对抗性扰动,攻击黑盒视频模型。具体地说,由于观察到图像和视频框架之间的低位特征空间相似,我们提出了简单而有效的跨式攻击方法,称为“图像(I2V)攻击”攻击。I2V通过尽量减少从对抗性和良性例子中测试前的77-88型图像模型的相似性,然后将生成的对抗性框架结合到对黑盒攻击的黑色框攻击,V2 图像和视频框架之间的低位化成功率模型,可以分别实现高比例的BV2 成功度实验。I 能够实现V2攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击