arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.02343cs.CV
收藏

Reflection Backdoor:一种对深度神经网络的自然后门攻击

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

Yunfei Liu, Xingjun Ma, James Bailey, Feng Lu

摘要:

最近的研究表明,DNN可能会受到训练时精心策划的后门攻击的损害。后门攻击通过将后门模式注入到一小部分训练数据中来将后门安装到受害者模型中。在测试时,受害者模型在干净的测试数据上表现正常,但只要测试示例中存在后门模式,就始终预测特定的(可能不正确的)目标类。虽然现有的后门攻击是有效的,但它们并不隐秘。对训练数据或标签进行的修改通常是可疑的,并且可以通过简单的数据过滤或人工检查容易地检测到。在本文中,我们提出了一种新型的后门攻击的灵感来自一个重要的自然现象:反射。使用物理反射模型的数学建模,我们提出反射后门(Refool)植物反射作为后门到受害者模型。我们在3个计算机视觉任务和5个数据集上证明,Refool可以以高成功率攻击最先进的DNN,并且可以抵抗最先进的后门防御。

英文摘要:

Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test time, the victim model behaves normally on clean test data, yet consistently predicts a specific (likely incorrect) target class whenever the backdoor pattern is present in a test example. While existing backdoor attacks are effective, they are not stealthy. The modifications made on training data or labels are often suspicious and can be easily detected by simple data filtering or human inspection. In this paper, we present a new type of backdoor attack inspired by an important natural phenomenon: reflection. Using mathematical modeling of physical reflection models, we propose reflection backdoor (Refool) to plant reflections as backdoor into a victim model. We demonstrate on 3 computer vision tasks and 5 datasets that, Refool can attack state-of-the-art DNNs with high success rate, and is resistant to state-of-the-art backdoor defenses.

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。

↑