FENCE:约束环境下对神经网络的可行规避攻击
FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments
摘要:
随着深度神经网络(DNN)的进步在许多关键应用中展示出前所未有的性能水平,它们对攻击的脆弱性仍然是一个悬而未决的问题。我们考虑在受限环境中测试时对深度学习的规避攻击,其中需要满足特征之间的依赖关系。这些情况可能在表格数据中自然出现,也可能是特定应用领域的特征工程的结果,例如网络安全中的威胁检测。我们提出了一个通用的迭代梯度为基础的框架,称为FENCE的手工规避攻击,考虑到具体的约束域和应用程序的要求。我们将其应用于针对两个网络安全应用训练的前馈神经网络:网络流量僵尸网络分类和恶意域分类,以生成可行的对抗性示例。我们广泛评估了攻击的成功率和性能,比较了它们在几个基线上的改进,并分析了影响攻击成功率的因素,包括优化目标和数据不平衡。我们表明,以最小的努力(例如,生成12个额外的网络连接),攻击者可以将模型的预测从恶意类别更改为良性类别,并逃避分类器。我们发现,在不平衡程度较高的数据集上训练的模型更容易受到我们的FENCE攻击。最后,我们展示了在约束域中进行对抗性训练的潜力,以提高模型对这些规避攻击的弹性。
英文摘要:
As advances in Deep Neural Networks (DNNs) demonstrate unprecedented levels of performance in many critical applications, their vulnerability to attacks is still an open question. We consider evasion attacks at testing time against Deep Learning in constrained environments, in which dependencies between features need to be satisfied. These situations may arise naturally in tabular data or may be the result of feature engineering in specific application domains, such as threat detection in cyber security. We propose a general iterative gradient-based framework called FENCE for crafting evasion attacks that take into consideration the specifics of constrained domains and application requirements. We apply it against Feed-Forward Neural Networks trained for two cyber security applications: network traffic botnet classification and malicious domain classification, to generate feasible adversarial examples. We extensively evaluate the success rate and performance of our attacks, compare their improvement over several baselines, and analyze factors that impact the attack success rate, including the optimization objective and the data imbalance. We show that with minimal effort (e.g., generating 12 additional network connections), an attacker can change the model's prediction from the Malicious class to Benign and evade the classifier. We show that models trained on datasets with higher imbalance are more vulnerable to our FENCE attacks. Finally, we demonstrate the potential of performing adversarial training in constrained domains to increase the model resilience against these evasion 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。