Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency

There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans are able to recognize objects that appear out of place in a scene or along with other unlikely objects, we augment the DNN with a system that learns context consistency rules during training and checks for the violations of the same during testing. Our approach builds a set of auto-encoders, one for each object class, appropriately trained so as to output a discrepancy between the input and output if an added adversarial perturbation violates context consistency rules. Experiments on PASCAL VOC and MS COCO show that our method effectively detects various adversarial attacks and achieves high ROC-AUC (over 0.95 in most cases); this corresponds to over 20% improvement over a state-of-the-art context-agnostic method.

[1]  Cordelia Schmid,et al.  Modeling Visual Context is Key to Augmenting Object Detection Datasets , 2018, ECCV.

[2]  Yichen Wei,et al.  Relation Networks for Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[3]  Zhitao Gong,et al.  Adversarial and Clean Data Are Not Twins , 2017, aiDM@SIGMOD.

[4]  Wenbin Li,et al.  High Accuracy Individual Identification Model of Crested Ibis (Nipponia Nippon) Based on Autoencoder With Self-Attention , 2020, IEEE Access.

[5]  Tristan Perez,et al.  Mixtures of Lightweight Deep Convolutional Neural Networks: Applied to Agricultural Robotics , 2017, IEEE Robotics and Automation Letters.

[6]  Xingxing Wei,et al.  Identifying and Resisting Adversarial Videos Using Temporal Consistency , 2019, ArXiv.

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

[8]  Antonio Torralba,et al.  A Tree-Based Context Model for Object Recognition , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[10]  David A. Forsyth,et al.  SafetyNet: Detecting and Rejecting Adversarial Examples Robustly , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Kevin Gimpel,et al.  Early Methods for Detecting Adversarial Images , 2016, ICLR.

[12]  Amit K. Roy-Chowdhury,et al.  Context-Aware Activity Recognition and Anomaly Detection in Video , 2013, IEEE Journal of Selected Topics in Signal Processing.

[13]  Xin Li,et al.  Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[14]  Dawn Song,et al.  Physical Adversarial Examples for Object Detectors , 2018, WOOT @ USENIX Security Symposium.

[15]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

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

[17]  Amit K. Roy-Chowdhury,et al.  Adversarial Perturbations Against Real-Time Video Classification Systems , 2018, NDSS.

[18]  Antonio Torralba,et al.  Top-down control of visual attention in object detection , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[19]  Sanja Fidler,et al.  The Role of Context for Object Detection and Semantic Segmentation in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Atul Prakash,et al.  Robust Physical-World Attacks on Deep Learning Visual Classification , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[23]  Dilek Z. Hakkani-Tür,et al.  MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension , 2020, AAAI.

[24]  Srikanth V. Krishnamurthy,et al.  A4 : Evading Learning-based Adblockers , 2020, ArXiv.

[25]  Yu-Ru Lin,et al.  Voila: Visual Anomaly Detection and Monitoring with Streaming Spatiotemporal Data , 2018, IEEE Transactions on Visualization and Computer Graphics.

[26]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[27]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Dongdong Hou,et al.  Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[30]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[31]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[33]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[35]  Jian Dong,et al.  Attentive Contexts for Object Detection , 2016, IEEE Transactions on Multimedia.

[36]  Xinlei Chen,et al.  Spatial Memory for Context Reasoning in Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[38]  Ohad Ben-Shahar,et al.  Exploring the Bounds of the Utility of Context for Object Detection , 2017, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Shiguang Shan,et al.  Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Jonghyun Choi,et al.  Learning Temporal Regularity in Video Sequences , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[42]  Xiaofeng Wang,et al.  Detecting Adversarial Image Examples in Deep Neural Networks with Adaptive Noise Reduction , 2017, IEEE Transactions on Dependable and Secure Computing.

[43]  Logan Engstrom,et al.  Synthesizing Robust Adversarial Examples , 2017, ICML.

[44]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[45]  J. Henderson,et al.  Does consistent scene context facilitate object perception? , 1998, Journal of experimental psychology. General.

[46]  Duen Horng Chau,et al.  ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector , 2018, ECML/PKDD.

[47]  Yanjun Qi,et al.  Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks , 2017, NDSS.

[48]  David Wagner,et al.  Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods , 2017, AISec@CCS.

[49]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[50]  Xiaochun Cao,et al.  ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[51]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Mingyan Liu,et al.  Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation , 2018, ECCV.

[53]  Ruigang Liang,et al.  Seeing isn't Believing: Towards More Robust Adversarial Attack Against Real World Object Detectors , 2019, CCS.

[54]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[55]  Nannan Li,et al.  Video anomaly detection based on a hierarchical activity discovery within spatio-temporal contexts , 2014, Neurocomputing.

[56]  Amit K. Roy-Chowdhury,et al.  Online Adaptation for Joint Scene and Object Classification , 2016, ECCV.

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

[58]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.