Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

24 May 2022

ArXiv (abs)PDF HTML Github (26★)

Papers citing "Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free"

39 / 39 papers shown

Title
GANs Can Play Lottery Tickets Too Xuxi Chen Zhenyu Zhang Yongduo Sui Tianlong Chen GAN 66 58 0 31 May 2021
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild Basel Alomair Aleksander Madry Yue Liu Tom Goldstein SILM 102 282 0 18 Dec 2020
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models Tianlong Chen Jonathan Frankle Shiyu Chang Sijia Liu Yang Zhang Michael Carbin Zhangyang Wang 66 123 0 12 Dec 2020
Poisoned classifiers are not only backdoored, they are fundamentally broken Mingjie Sun Siddhant Agarwal J. Zico Kolter 52 26 0 18 Oct 2020
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks Yunfei Liu Xingjun Ma James Bailey Feng Lu AAML 96 516 0 05 Jul 2020
ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks Miguel Villarreal-Vasquez B. Bhargava AAML 84 38 0 01 Jul 2020
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks Avi Schwarzschild Micah Goldblum Arjun Gupta John P. Dickerson Tom Goldstein AAML TDI 98 164 0 22 Jun 2020
Rethinking the Trigger of Backdoor Attack Yiming Li Tongqing Zhai Baoyuan Wu Yong Jiang Zhifeng Li Shutao Xia LLMSV 67 150 0 09 Apr 2020
Comparing Rewinding and Fine-tuning in Neural Network Pruning Alex Renda Jonathan Frankle Michael Carbin 283 388 0 05 Mar 2020
Defending against Backdoor Attack on Deep Neural Networks Kaidi Xu Sijia Liu Pin-Yu Chen Pu Zhao Xinyu Lin Xue Lin AAML 68 49 0 26 Feb 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 140 1,181 0 12 Jan 2020
PyHessian: Neural Networks Through the Lens of the Hessian Z. Yao A. Gholami Kurt Keutzer Michael W. Mahoney ODL 66 303 0 16 Dec 2019
Linear Mode Connectivity and the Lottery Ticket Hypothesis Jonathan Frankle Gintare Karolina Dziugaite Daniel M. Roy Michael Carbin MoMe 163 628 0 11 Dec 2019
Hidden Trigger Backdoor Attacks Aniruddha Saha Akshayvarun Subramanya Hamed Pirsiavash 89 627 0 30 Sep 2019
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems Wenbo Guo Lun Wang Masashi Sugiyama Min Du Basel Alomair 73 230 0 02 Aug 2019
Importance Estimation for Neural Network Pruning Pavlo Molchanov Arun Mallya Stephen Tyree I. Frosio Jan Kautz 3DPC 81 885 0 25 Jun 2019
Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP Haonan Yu Sergey Edunov Yuandong Tian Ari S. Morcos 52 150 0 06 Jun 2019
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets Chen Zhu Wenjie Huang Ali Shafahi Hengduo Li Gavin Taylor Christoph Studer Tom Goldstein 89 285 0 15 May 2019
The State of Sparsity in Deep Neural Networks Trevor Gale Erich Elsen Sara Hooker 163 762 0 25 Feb 2019
Model Compression with Adversarial Robustness: A Unified Optimization Framework Shupeng Gui Haotao Wang Chen Yu Haichuan Yang Zhangyang Wang Ji Liu MQ 59 138 0 10 Feb 2019
ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers Ao Ren Tianyun Zhang Shaokai Ye Jiayu Li Wenyao Xu Xuehai Qian Xinyu Lin Yanzhi Wang MQ 95 161 0 31 Dec 2018
SNIP: Single-shot Network Pruning based on Connection Sensitivity Namhoon Lee Thalaiyasingam Ajanthan Philip Torr VLM 266 1,207 0 04 Oct 2018
Robustness May Be at Odds with Accuracy Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner Aleksander Madry AAML 108 1,782 0 30 May 2018
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning Matthew Jagielski Alina Oprea Battista Biggio Chang-rui Liu Cristina Nita-Rotaru Yue Liu AAML 85 764 0 01 Apr 2018
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Jonathan Frankle Michael Carbin 261 3,485 0 09 Mar 2018
Stochastic Activation Pruning for Robust Adversarial Defense Guneet Singh Dhillon Kamyar Azizzadenesheli Zachary Chase Lipton Jeremy Bernstein Jean Kossaifi Aran Khanna Anima Anandkumar AAML 81 547 0 05 Mar 2018
Essentially No Barriers in Neural Network Energy Landscape Felix Dräxler K. Veschgini M. Salmhofer Fred Hamprecht MoMe 118 434 0 02 Mar 2018
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning Xinyun Chen Chang-rui Liu Yue Liu Kimberly Lu Basel Alomair AAML SILM 143 1,853 0 15 Dec 2017
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain Tianyu Gu Brendan Dolan-Gavitt S. Garg SILM 130 1,782 0 22 Aug 2017
Learning Efficient Convolutional Networks through Network Slimming Zhuang Liu Jianguo Li Zhiqiang Shen Gao Huang Shoumeng Yan Changshui Zhang 125 2,426 0 22 Aug 2017
Evasion Attacks against Machine Learning at Test Time Battista Biggio Igino Corona Davide Maiorca B. Nelson Nedim Srndic Pavel Laskov Giorgio Giacinto Fabio Roli AAML 163 2,160 0 21 Aug 2017
Channel Pruning for Accelerating Very Deep Neural Networks Yihui He Xiangyu Zhang Jian Sun 204 2,529 0 19 Jul 2017
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 317 12,131 0 19 Jun 2017
DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples Ji Gao Beilun Wang Zeming Lin Weilin Xu Yanjun Qi AAML 49 90 0 22 Feb 2017
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 472 3,148 0 04 Nov 2016
Towards Evaluating the Robustness of Neural Networks Nicholas Carlini D. Wagner OOD AAML 282 8,583 0 16 Aug 2016
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs Liang-Chieh Chen George Papandreou Iasonas Kokkinos Kevin Patrick Murphy Alan Yuille SSeg 267 18,267 0 02 Jun 2016
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding Song Han Huizi Mao W. Dally 3DGS 263 8,859 0 01 Oct 2015
Learning both Weights and Connections for Efficient Neural Networks Song Han Jeff Pool J. Tran W. Dally CVBM 313 6,700 0 08 Jun 2015