arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.01239cs.LG
收藏

抗粘附深度神经网络及其在恶意软件检测中的应用

Adversary Resistant Deep Neural Networks with an Application to Malware Detection

Pennsylvania State University(宾夕法尼亚州立大学);McGill University(麦吉尔大学)

Qinglong Wang, Wenbo Guo, Kaixuan Zhang, Alexander G. Ororbia, Xinyu Xing, C. Lee Giles, Xue Liu

摘要:

除了在围棋上的胜利,深度学习在信息检索、计算机视觉和语音识别方面也有许多成功的应用。在网络安全领域,越来越多的公司对深度学习的潜力感到兴奋,并开始将其用于各种安全事件,其中最受欢迎的是恶意软件检测。这些公司声称,深度学习(DL)可以帮助扭转恶意软件感染的趋势。然而,深度神经网络(DNN)容易受到对抗性样本的影响,这是一个困扰大多数(如果不是所有)统计学习模型的缺陷。最近的研究表明,那些有恶意意图的人可以通过利用这个缺陷轻松规避深度学习驱动的恶意软件检测。为了解决这个问题,以前的工作已经开发了各种防御机制,无论是增加训练数据或提高模型的复杂性。然而,在对DNN的根本缺陷进行彻底分析后,我们发现当前防御的有效性是有限的,更重要的是,无法提供理论保证来对抗基于样本的攻击。因此,我们提出了一种新的对抗技术,通过随机取消样本中的特征来阻止攻击者构建有影响力的对抗样本。在这项工作中,我们评估了我们提出的技术对现实世界的数据集与14,679恶意软件变种和17,399良性程序。我们在理论上验证了我们的技术的鲁棒性,并在经验上表明,我们的技术显着提高了DNN对对抗样本的鲁棒性,同时保持了高的分类准确性。为了证明我们提出的方法的普遍适用性,我们还使用MNIST和CIFAR-10数据集进行实验,通常用于图像识别研究。

英文摘要:

Beyond its highly publicized victories in Go, there have been numerous successful applications of deep learning in information retrieval, computer vision and speech recognition. In cybersecurity, an increasing number of companies have become excited about the potential of deep learning, and have started to use it for various security incidents, the most popular being malware detection. These companies assert that deep learning (DL) could help turn the tide in the battle against malware infections. However, deep neural networks (DNNs) are vulnerable to adversarial samples, a flaw that plagues most if not all statistical learning models. Recent research has demonstrated that those with malicious intent can easily circumvent deep learning-powered malware detection by exploiting this flaw. In order to address this problem, previous work has developed various defense mechanisms that either augmenting training data or enhance model's complexity. However, after a thorough analysis of the fundamental flaw in DNNs, we discover that the effectiveness of current defenses is limited and, more importantly, cannot provide theoretical guarantees as to their robustness against adversarial sampled-based attacks. As such, we propose a new adversary resistant technique that obstructs attackers from constructing impactful adversarial samples by randomly nullifying features within samples. In this work, we evaluate our proposed technique against a real world dataset with 14,679 malware variants and 17,399 benign programs. We theoretically validate the robustness of our technique, and empirically show that our technique significantly boosts DNN robustness to adversarial samples while maintaining high accuracy in classification. To demonstrate the general applicability of our proposed method, we also conduct experiments using the MNIST and CIFAR-10 datasets, generally used in image recognition research.

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。

↑