A defense method against backdoor attacks on neural networks

Albert, 2002, Statistical mechanics of complex networks, Reviews of Modern Physics, 74, 47, 10.1103/RevModPhys.74.47 Albert, 2000, Error and attack tolerance of complex networks, Nature, 406, 378, 10.1038/35019019 Amazon, 2015 Bakator, 2018, Deep learning and medical diagnosis: A review of literature, Multimodal Technologies and Interaction, 2, 47, 10.3390/mti2030047 Barabasi, 2009, Scale-free networks: a decade and beyond, Science, 325, 412, 10.1126/science.1173299 Barabasi, 1999, Emergence of scaling in random networks, Science, 286, 509, 10.1126/science.286.5439.509 Barabasi, 2004, Network biology: understanding the cell’s functional organization, Nature Reviews Genetics, 5, 101, 10.1038/nrg1272 Bertsimas, 2020, Sparse high-dimensional regression: Exact scalable algorithms and phase transitions, The Annals of Statistics, 48, 300, 10.1214/18-AOS1804 Bisong, 2019, Google cloud machine learning engine (Cloud MLE), 545 Bohland, 2001, Efficient associative memory using small-world architecture, Neurocomputing, 38, 489, 10.1016/S0925-2312(01)00378-2 Bottou, 2011, 13 The tradeoffs of large-scale learning, Optimization for Machine Learning, 351, 10.7551/mitpress/8996.003.0015 Chen, 2019, DeepInspect: A Black-box Trojan detection and mitigation framework for deep neural networks, 4658 Chen, 2017 Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2015). Deepdriving: Learning affordance for direct perception in autonomous driving. In Proceedings of the IEEE international conference on computer vision (pp. 2722–2730). Deng, 2012, The mnist database of handwritten digit images for machine learning research [best of the web], IEEE Signal Processing Magazine, 29, 141, 10.1109/MSP.2012.2211477 Deng, 2007, Collective behavior of a small-world recurrent neural system with scale-free distribution, IEEE Transactions on Neural Networks, 18, 1364, 10.1109/TNN.2007.894082 Eguiluz, 2005, Scale-free brain functional networks, Physical Review Letters, 94, 10.1103/PhysRevLett.94.018102 Gao, Y., Xu, C., Wang, D., Chen, S., Ranasinghe, D. C., & Nepal, S. (2019). Strip: A defence against trojan attacks on deep neural networks. In Proceedings of the 35th annual computer security applications conference (pp. 113–125). Geigel, 2013, Neural network trojan, Journal of Computer Security, 21, 191, 10.3233/JCS-2012-0460 Goodfellow, 2016, 1 Gros, 2010, 157 Gu, 2017 Guo, 2018 Kaviani, 2020 Kaviani, 2021, Defense against neural trojan attacks: A survey, Neurocomputing, 423, 651, 10.1016/j.neucom.2020.07.133 Kaviani, 2020, Application of complex systems in neural networks against Backdoor attacks, 57 Kim, 2004, Performance of networks of artificial neurons: The role of clustering, Physical Review E, 69, 10.1103/PhysRevE.69.045101 Liu, 2018, Fine-pruning: Defending against backdooring attacks on deep neural networks, 273 Liu, 2019, ABS: Scanning neural networks for back-doors by artificial brain stimulation, 1265 Liu, 2017 Liu, 2017, Neural trojans, 45 Microsoft Corp., Microsoft Corp., (0000). Azure Batch AI Training, https://batchaitraining.azure.com/. Mnih, 2013 Mocanu, 2016, A topological insight into restricted boltzmann machines, Machine Learning, 104, 243, 10.1007/s10994-016-5570-z Mocanu, 2017 Mocanu, 2018, Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science, Nature communications, 9, 1, 10.1038/s41467-018-04316-3 Monteiro, 2016, A model for improving the learning curves of artificial neural networks, PLoS One, 11, 10.1371/journal.pone.0149874 Morita, 2001, Geometrical structure of the neuronal network of Caenorhabditis elegans, Physica A: Statistical Mechanics and its Applications, 298, 553, 10.1016/S0378-4371(01)00266-7 Nazzal, 2008, 1 Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263–7271). Ren, 2015 Rosenblatt, 1958, The perceptron: a probabilistic model for information storage and organization in the brain, Psychological Review, 65, 386, 10.1037/h0042519 Rumelhart, 1986, Learning representations by back-propagating errors, Nature, 323, 533, 10.1038/323533a0 Saha, A., Subramanya, A., & Pirsiavash, H. (2020). Hidden trigger backdoor attacks. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34 (pp. 11957–11965). (07). Silver, 2016, Mastering the game of Go with deep neural networks and tree search, Nature, 529, 484, 10.1038/nature16961 Simard, 2005, Fastest learning in small-world neural networks, Physics Letters. A, 336, 8, 10.1016/j.physleta.2004.12.078 Simonyan, 2014 Stauffer, 2003, Efficient Hopfield pattern recognition on a scale-free neural network, The European Physical Journal B, 32, 395, 10.1140/epjb/e2003-00114-7 Sze, 2017, Efficient processing of deep neural networks: A tutorial and survey, Proceedings of the IEEE, 105, 2295, 10.1109/JPROC.2017.2761740 Turner, 2018 Turner, 2019 Wang, 2019, Neural cleanse: Identifying and mitigating backdoor attacks in neural networks, 707 Watts, 1998, Collective dynamics of ‘small-world’networks, Nature, 393, 440, 10.1038/30918 Wei, 2009, Application of entropy to the pruning algorithm of BP neural network, Information and Control, 38, 633 Xu, 2019 Zha, 2020, Robust deep co-saliency detection with group semantic and pyramid attention, 1 Zhang, 2010, A node pruning algorithm for feedforward neural network based on neural complexity, 406 Zhang, 2021, Flexible transmitter network, Neural Computation, 33, 2951 Zou, 2018