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 1612.01401cs.LG
收藏

学习抗逆深度神经网络

Learning Adversary-Resistant Deep Neural Networks

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

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

摘要:

深度神经网络(DNN)已被证明在大量机器学习任务中非常有效,最近的例子包括网络安全和自动驾驶汽车。尽管DNN在这些应用中具有卓越的性能,但最近的研究表明,这些模型容易受到利用其设计中的根本缺陷的特定类型的攻击。这种攻击包括生成被称为对抗样本的特定合成示例。这些样本是通过稍微操纵真实数据点来构造的,以“欺骗”原始DNN模型,迫使它以高置信度错误分类先前正确分类的样本。如果DNN要用于网络安全等关键应用,解决模型中的这一缺陷至关重要。为了提高DNN模型的鲁棒性,前人提出了各种学习算法,但都属于“通过模糊来实现安全”的策略。这意味着只有当一个人能够从对手那里隐藏学习算法时,安全性才能得到保证。一旦学习技术被公开,受这些防御机制保护的DNN仍然容易受到对抗性样本的影响。在这项工作中,我们调查了以前的研究工作中共享的这个问题,并提出了一种通用的方法来升级DNN对对抗性样本的抵抗力。更具体地说,我们的方法将数据转换模块与DNN集成在一起,即使我们揭示了底层的学习算法,也使其具有鲁棒性。为了证明我们提出的方法的通用性及其处理网络安全应用的潜力,我们评估了我们的方法和其他几个现有的解决方案公开可用的数据集。我们的研究结果表明,我们的方法通常提供优越的分类性能和阻力相比,最先进的解决方案。

英文摘要:

Deep neural networks (DNNs) have proven to be quite effective in a vast array of machine learning tasks, with recent examples in cyber security and autonomous vehicles. Despite the superior performance of DNNs in these applications, it has been recently shown that these models are susceptible to a particular type of attack that exploits a fundamental flaw in their design. This attack consists of generating particular synthetic examples referred to as adversarial samples. These samples are constructed by slightly manipulating real data-points in order to "fool" the original DNN model, forcing it to mis-classify previously correctly classified samples with high confidence. Addressing this flaw in the model is essential if DNNs are to be used in critical applications such as those in cyber security. Previous work has provided various learning algorithms to enhance the robustness of DNN models, and they all fall into the tactic of "security through obscurity". This means security can be guaranteed only if one can obscure the learning algorithms from adversaries. Once the learning technique is disclosed, DNNs protected by these defense mechanisms are still susceptible to adversarial samples. In this work, we investigate this issue shared across previous research work and propose a generic approach to escalate a DNN's resistance to adversarial samples. More specifically, our approach integrates a data transformation module with a DNN, making it robust even if we reveal the underlying learning algorithm. To demonstrate the generality of our proposed approach and its potential for handling cyber security applications, we evaluate our method and several other existing solutions on datasets publicly available. Our results indicate that our approach typically provides superior classification performance and resistance in comparison with state-of-art solutions.

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。

↑