Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Keywords

Adversarial system, Deep learning, Artificial intelligence, Computer science, Adversarial machine learning

References

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick — 2015
• Learning representations by back-propagating errorsDavid E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams — 1986
• Digital selection and analogue amplification coexist in a cortex-inspired silicon circuitRichard H. R. Hahnloser, Rahul Sarpeshkar, Misha Mahowald — 2000
• Intriguing properties of neural networksChristian Szegedy, Wojciech Zaremba, Ilya Sutskever — 2013
• Analysis of classifiers’ robustness to adversarial perturbationsAlhussein Fawzi, Omar Fawzi, Pascal Frossard — 2015
• Very Deep Convolutional Networks for Large-Scale Image RecognitionKaren Simonyan, Andrew Zisserman — 2014
• Distilling the Knowledge in a Neural NetworkGeoffrey E. Hinton, Oriol Vinyals, Jay B. Dean — 2015
• Deep Learning Face Attributes in the WildZiwei Liu, Ping Luo, Xiaogang Wang — 2014
• Towards Deep Neural Network Architectures Robust to Adversarial ExamplesShixiang Gu, Luca Rigazio — 2014
• Fully convolutional networks for semantic segmentationJonathan Long, Evan Shelhamer, Trevor Darrell — 2014
• Deep neural networks are easily fooled: High confidence predictions for unrecognizable imagesAnh‐Tu Nguyen, Jason Yosinski, Jeff Clune — 2014
• MatConvNet: Convolutional Neural Networks for MATLABAndrea Vedaldi, Karel Lenc — 2014
• Online particle detection with Neural Networks based on topological calorimetry informationT Ciodaro, D Deva, J. M. Seixas — 2012
• Return of the Devil in the Details: Delving Deep into Convolutional NetsKen Chatfield, Karen Simonyan, Andrea Vedaldi — 2014
• Deep Neural Nets as a Method for Quantitative Structure-Activity RelationshipsJunshui Ma, Robert P. Sheridan, Andy Liaw — 2015
• Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber — 1997
• Learning Deep Architectures for AIYoshua Bengio — 2007
• Practical Methods of Optimization: Fletcher/Practical Methods of OptimizationR. Ian Fletcher — 2000
• The human splicing code reveals new insights into the genetic determinants of diseaseHui Xiong, Babak Alipanahi, Leo J. Lee — 2014
• Going deeper with convolutionsChristian Szegedy, Wei Liu, Yangqing Jia — 2014

Cited by

• Global Guarantees for Enforcing Deep Generative Priors by Empirical RiskPaul Hand, Vladislav Voroninski — 2017
• Deep packet: a novel approach for encrypted traffic classification using deep learningMohammad Lotfollahi, Mahdi Jafari Siavoshani, Ramin Shirali Hossein Zade — 2017
• A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources ScientistsChaopeng Shen — 2017
• High Dimensional Spaces, Deep Learning and Adversarial ExamplesSimant Dube — 2018
• Security and Privacy Approaches in Mixed RealityJaybie A. De Guzman, Kanchana Thilakarathna, Aruna Seneviratne — 2018
• Robustness of Rotation-Equivariant Networks to Adversarial PerturbationsBéranger Dumont, Simona Maggio, Pablo Montalvo — 2018
• Detecting Adversarial Examples via Neural FingerprintingSumanth Dathathri, Stephan Zheng, Yin, Tianwei — 2018
• On Generation of Adversarial Examples using Convex ProgrammingEmilio Rafael Balda, Arash Behboodi, Rudolf Mathar — 2018
• Defending against Adversarial Images using Basis Functions TransformationsUri Shaham, James Garritano, Yutaro Yamada — 2018
• The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial ExamplesAyse Elvan Aydemir, Alptekin Temizel, Tuğba Taşkaya Temizel — 2018
• ADef: an Iterative Algorithm to Construct Adversarial DeformationsRima Alaifari, Giovanni S. Alberti, Tandri Gauksson — 2018
• Fast Neural Network Training on FPGA Using Quasi-Newton Optimization MethodQiang Liu, Jia Liu, Ruoyu Sang — 2018
• Training verified learners with learned verifiersKrishnamurthy Dvijotham, Sven Gowal, Robert Stanforth — 2018
• Featurized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic InferenceRuying Bao, Sihang Liang, Qingcan Wang — 2018
• Bidirectional Learning for Robust Neural NetworksSidney Pontes-Filho, Marcus Liwicki — 2018
• Adversarial Attacks on Face Detectors Using Neural Net Based Constrained OptimizationAvishek Joey Bose, Parham Aarabi — 2018
• Hardware Trojan Attacks on Neural NetworksJoseph Clements, Yingjie Lao — 2018
• Basic functional trade-offs in cognition: An integrative framework.Marco Del Giudice, Bernard J. Crespi — 2018
• Local Gradients Smoothing: Defense Against Localized Adversarial AttacksMuzammal Naseer, Salman Khan, Fatih Porikli — 2018
• A general metric for identifying adversarial imagesSiddharth Krishna Kumar — 2018

Related papers

• ADVANCEMENT OF ATTACK AND DEFENSE TECHNIQUES IN ADVERSARIAL MACHINELEARNINGTrupti Mandar Joshi, Shikha Agrawal, Sanjay Silakari — 2020
• Adversarial Learning in Real-World Fraud Detection: Challenges and PerspectivesDaniele Lunghi, Alkis Simitsis, Olivier Caelen — 2023
• An Optimal Control View of Adversarial Machine LearningXiaojin Zhu — 2018
• Analyzing the Impact of Adversarial Examples on Explainable Machine LearningPrathyusha Devabhakthini, Sasmita Parida, Raj Mani Shukla — 2023
• On The Detection Of Adversarial Attacks Through Reliable AIIvan Vaccari, Alberto Carlevaro, Sara Narteni — 2022
• Adversarial Machine Learning: Perspectives from Adversarial Risk AnalysisDavid Rı́os Insua, Roi Naveiro, Víctor Gallego — 2020
• Machine Learning in Adversarial SettingsPatrick McDaniel, Nicolas Papernot, Z. Berkay Celik — 2016
• Adversarial Evasion Attacks Practicality in Networks: Testing the Impact of Dynamic LearningMohamed el Shehaby, Ashraf Matrawy — 2023
• Global Adversarial Attacks for Assessing Deep Learning RobustnessHanbin Hu, Mit Shah, Jianhua Z. Huang — 2019
• A Comparative Study on Adversarial Attacks and Defense MechanismsBhavana Kumbar, Ankita Mane, Varsha Chalageri — 2022