arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.06107cs.CVcs.CRcs.LG
收藏

对抗性的例子也很有用!

Adversarial examples are useful too!

Ali Borji

摘要:

深度学习已经走过了漫长的道路,并取得了前所未有的成功。然而,尽管精确度很高,但深层模型是脆弱的,很容易被难以察觉的对抗性扰动所欺骗。与常见的推理时间攻击相比,后门(\aka特洛伊木马)攻击针对模型构建的训练阶段,并且非常难以对抗,因为a)模型在原始测试集上表现正常,b)增强扰动可能很小,可能只影响很少的训练样本。在这里,我提出了一种新的方法来判断一个模型是否受到了后门攻击。其想法是使用FGSM等传统攻击生成有针对性或无针对性的对抗性示例,然后将其反馈给分类器。通过计算不同类别的图像的统计数据(这里简单地说是平均图),并将它们与参考模型的统计数据进行比较,可以在视觉上定位扰动区域并揭示攻击。

英文摘要:

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time attacks, Backdoor (\aka Trojan) attacks target the training phase of model construction, and are extremely difficult to combat since a) the model behaves normally on a pristine testing set and b) the augmented perturbations can be minute and may only affect few training samples. Here, I propose a new method to tell whether a model has been subject to a backdoor attack. The idea is to generate adversarial examples, targeted or untargeted, using conventional attacks such as FGSM and then feed them back to the classifier. By computing the statistics (here simply mean maps) of the images in different categories and comparing them with the statistics of a reference model, it is possible to visually locate the perturbed regions and unveil the attack.

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。

↑