Efficient detection of adversarial images
arXiv:2007.04564
Abstract
In this paper, detection of deception attack on deep neural network (DNN) based image classification in autonomous and cyber-physical systems is considered. Several studies have shown the vulnerability of DNN to malicious deception attacks. In such attacks, some or all pixel values of an image are modified by an external attacker, so that the change is almost invisible to the human eye but significant enough for a DNN-based classifier to misclassify it. This paper first proposes a novel pre-processing technique that facilitates the detection of such modified images under any DNN-based image classifier as well as the attacker model. The proposed pre-processing algorithm involves a certain combination of principal component analysis (PCA)-based decomposition of the image, and random perturbation based detection to reduce computational complexity. Next, an adaptive version of this algorithm is proposed where a random number of perturbations are chosen adaptively using a doubly-threshold policy, and the threshold values are learnt via stochastic approximation in order to minimize the expected number of perturbations subject to constraints on the false alarm and missed detection probabilities. Numerical experiments show that the proposed detection scheme outperforms a competing algorithm while achieving reasonably low computational complexity.
arXiv comment10 pages, 3 figures, 3 algorithms, 8 tables. Extension of the Conference paper:- Kartik Mundra, Rahul Modpur, Arpan Chattopadhyay, and Indra Narayan Kar. Adversarial image detection in cyber-physical systems. In Proceedings of the 1st ACM Workshop on Autonomous and Intelligent Mobile Systems, pages 1-5, 2020. Can be found at https://dl.acm.org/doi/abs/10.1145/3377283.3377285
References in corpus (11)
- Scikit-learn: Machine Learning in Python
- Distilling the Knowledge in a Neural Network
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Do Deep Nets Really Need to be Deep?
- Robust Physical-World Attacks on Deep Learning Models
- Detecting Adversarial Samples from Artifacts
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
- Defensive Distillation is Not Robust to Adversarial Examples
- Early Methods for Detecting Adversarial Images
- Detecting Adversarial Samples for Deep Neural Networks through Mutation Testing
- Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction