arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.08316cs.CR
收藏

用于作者身份识别的对抗性二进制文件

Adversarial Binaries for Authorship Identification

Xiaozhu Meng, Barton P. Miller, Somesh Jha

摘要:

二进制代码作者身份识别确定二进制程序的作者。现有技术已经将有监督的机器学习用于该任务。在本文中,我们从攻击者的角度来看这个问题。我们的目标是修改一个测试二进制文件,这样它不仅会导致预测错误,而且还保持了原始输入二进制文件的功能。对二进制代码的攻击本质上比对计算机视觉等领域的攻击更困难,在这些领域,攻击者可以独立地改变输入图像的每个像素,并且仍然保持有效的图像。对于二进制代码,即使翻转二进制的一位也可能导致二进制无效,在运行时崩溃,或丢失原始功能。我们调查了两种类型的攻击:无针对性的攻击,造成错误预测的任何不正确的作者,和有针对性的攻击,造成错误预测的一个特定的不正确的作者。我们开发了两个关键的攻击能力:特征向量修改,生成一个对抗性特征向量,它既对应于一个真实的二进制文件,又会导致所需的误预测,以及输入二进制修改,修改输入二进制文件以匹配对抗性特征向量,同时保持输入二进制文件的功能。我们评估了我们对使用最先进的作者归属方法训练的分类器的攻击。作者身份识别的分类器具有91%的平均准确率。我们的无针对性攻击平均成功率为96%,这表明我们可以有效地抑制作者身份信号。我们有针对性的攻击平均有46%的成功率,这表明模仿特定程序员的风格是可能的,但要困难得多。我们的攻击表明,现有的二进制代码作者身份识别技术依赖于代码的功能,很容易修改,因此容易受到攻击。

英文摘要:

Binary code authorship identification determines authors of a binary program. Existing techniques have used supervised machine learning for this task. In this paper, we look this problem from an attacker's perspective. We aim to modify a test binary, such that it not only causes misprediction but also maintains the functionality of the original input binary. Attacks against binary code are intrinsically more difficult than attacks against domains such as computer vision, where attackers can change each pixel of the input image independently and still maintain a valid image. For binary code, even flipping one bit of a binary may cause the binary to be invalid, to crash at the run-time, or to lose the original functionality. We investigate two types of attacks: untargeted attacks, causing misprediction to any of the incorrect authors, and targeted attacks, causing misprediction to a specific one among the incorrect authors. We develop two key attack capabilities: feature vector modification, generating an adversarial feature vector that both corresponds to a real binary and causes the required misprediction, and input binary modification, modifying the input binary to match the adversarial feature vector while maintaining the functionality of the input binary. We evaluated our attack against classifiers trained with a state-of-the-art method for authorship attribution. The classifiers for authorship identification have 91% accuracy on average. Our untargeted attack has a 96% success rate on average, showing that we can effectively suppress authorship signal. Our targeted attack has a 46% success rate on average, showing that it is possible, but significantly more difficult to impersonate a specific programmer's style. Our attack reveals that existing binary code authorship identification techniques rely on code features that are easy to modify, and thus are vulnerable to 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。

↑