arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.01023cs.CVcs.LG
收藏

通过细化特征表示减少对抗性扰动的影响

Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation

Shahid Bahonar University(沙希德·巴霍纳尔大学);University of Manitoba(曼尼托巴大学)

Nader Asadi, AmirMohammad Sarfi, Mehrdad Hosseinzadeh, Sahba Tahsini, Mahdi Eftekhari

摘要:

深度神经网络极易受到对抗性样本的攻击,这给这些最先进的模型带来了严重的安全问题。已经提出了许多防御方法来缓解这个问题。然而,它们中的许多依赖于目标模型的修改或额外训练。在这项工作中,我们分析调查每一层的非扰动和扰动图像的表示,并显示这些表示扰动的效果。因此,提出了一种基于白化着色变换的方法,以减少由对手造成的任何期望的层的误报。我们的方法可以应用于任何模型的任何层,而不需要任何修改或额外的训练。由于该层的表示的完全白化不容易区分,因此我们提出的方法对白盒攻击具有超强的鲁棒性。此外,我们证明了我们的方法对一些国家的最先进的黑盒攻击的强度。

英文摘要:

Deep neural networks are highly vulnerable to adversarial examples, which imposes severe security issues for these state-of-the-art models. Many defense methods have been proposed to mitigate this problem. However, a lot of them depend on modification or additional training of the target model. In this work, we analytically investigate each layer's representation of non-perturbed and perturbed images and show the effect of perturbations on each of these representations. Accordingly, a method based on whitening coloring transform is proposed in order to diminish the misrepresentation of any desirable layer caused by adversaries. Our method can be applied to any layer of any arbitrary model without the need of any modification or additional training. Due to the fact that the full whitening of the layer's representation is not easily differentiable, our proposed method is superbly robust against white-box attacks. Furthermore, we demonstrate the strength of our method against some state-of-the-art black-box attacks.

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。

↑