Crafting and Detecting Adversarial Web Requests

Deep learning (DL) techniques have provided state-of-the-art results for many machine learning tasks. In response to the increasing demand for web security, many researchers have been focusing on applying DL to detect web attacks. However, these works just pay attention to the detection accuracy, not the robustness of the detection model itself. In this paper, we proved that it is possible to generate adversarial web requests by modifying only a few characters of them, which can lead the existing DL based model to wrong predictions. The attackers may take this vulnerability to trigger false positive alarms or even disable the whole detection model. As the defensive measure, we propose to use a combined method of kernel density estimation and model uncertainty estimation to detect these adversaries. Through experiment, we report a ROC-AUC of over 95% of detecting these adversarial web requests.

[1]  Konstantin Berlin,et al.  eXpose: A Character-Level Convolutional Neural Network with Embeddings For Detecting Malicious URLs, File Paths and Registry Keys , 2017, ArXiv.

[2]  Keke Gai,et al.  Intrusion detection techniques for mobile cloud computing in heterogeneous 5G , 2016, Secur. Commun. Networks.

[3]  Howon Kim,et al.  Long Short Term Memory Recurrent Neural Network Classifier for Intrusion Detection , 2016, 2016 International Conference on Platform Technology and Service (PlatCon).

[4]  Sameep Mehta,et al.  Towards Crafting Text Adversarial Samples , 2017, ArXiv.

[5]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[6]  Yuefei Zhu,et al.  A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks , 2017, IEEE Access.

[7]  Jan Hendrik Metzen,et al.  On Detecting Adversarial Perturbations , 2017, ICLR.

[8]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[9]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[10]  Howon Kim,et al.  An Effective Intrusion Detection Classifier Using Long Short-Term Memory with Gradient Descent Optimization , 2017, 2017 International Conference on Platform Technology and Service (PlatCon).

[11]  Ming Zhang,et al.  A Deep Learning Method to Detect Web Attacks Using a Specially Designed CNN , 2017, ICONIP.

[12]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[13]  Mohammad Teshnehlab,et al.  An anomaly detection method to detect web attacks using Stacked Auto-Encoder , 2018, 2018 6th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS).

[14]  Ananthram Swami,et al.  The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[15]  Yuchen Wang,et al.  Learning and Applying Ontology for Machine Learning in Cyber Attack Detection , 2018, 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/ 12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE).

[16]  Ryan R. Curtin,et al.  Detecting Adversarial Samples from Artifacts , 2017, ArXiv.

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..