Blind Backdoors in Deep Learning Models

8 May 2020

Papers citing "Blind Backdoors in Deep Learning Models"

50 / 162 papers shown

Title
SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning Peizhuo Lv Pan Li Shenchen Zhu Shengzhi Zhang Kai Chen ... Fan Xiang Yuling Cai Hualong Ma Yingjun Zhang Guozhu Meng AAML 28 7 0 08 Sep 2022
Verifiable Encodings for Secure Homomorphic Analytics Sylvain Chatel Christian Knabenhans Apostolos Pyrgelis Carmela Troncoso Jean-Pierre Hubaux 28 19 0 28 Jul 2022
FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair Hui Xia Xiugui Yang X. Qian Rui Zhang AAML 27 0 0 26 Jul 2022
Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior Jean-Stanislas Denain Jacob Steinhardt AAML 39 7 0 27 Jun 2022
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning Baoyuan Wu Hongrui Chen Mingda Zhang Zihao Zhu Shaokui Wei Danni Yuan Chaoxiao Shen ELM AAML 33 138 0 25 Jun 2022
Defending Backdoor Attacks on Vision Transformer via Patch Processing Khoa D. Doan Yingjie Lao Peng Yang Ping Li AAML 25 21 0 24 Jun 2022
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks Ganqu Cui Lifan Yuan Bingxiang He Yangyi Chen Zhiyuan Liu Maosong Sun AAML ELM SILM 26 68 0 17 Jun 2022
Architectural Backdoors in Neural Networks Mikel Bober-Irizar Ilia Shumailov Yiren Zhao Robert D. Mullins Nicolas Papernot AAML 18 23 0 15 Jun 2022
Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion Si-An Chen Yi Zeng J. T.Wang Won Park Xun Chen Lingjuan Lyu Zhuoqing Mao R. Jia 8 3 0 14 Jun 2022
Adversarial RAW: Image-Scaling Attack Against Imaging Pipeline Junjian Li Honglong Chen AAML 11 2 0 02 Jun 2022
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples Xiangyu Qi Tinghao Xie Jiachen T. Wang Tong Wu Saeed Mahloujifar Prateek Mittal AAML 14 47 0 26 May 2022
Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets Florian Tramèr Reza Shokri Ayrton San Joaquin Hoang Minh Le Matthew Jagielski Sanghyun Hong Nicholas Carlini MIACV 36 107 0 31 Mar 2022
Trojan Horse Training for Breaking Defenses against Backdoor Attacks in Deep Learning Arezoo Rajabi Bhaskar Ramasubramanian Radha Poovendran AAML 17 4 0 25 Mar 2022
Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis Yuwei Sun H. Ochiai Jun Sakuma AAML FedML 37 15 0 22 Mar 2022
Dynamic Backdoors with Global Average Pooling Stefanos Koffas S. Picek Mauro Conti AAML 11 8 0 04 Mar 2022
Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving Xingshuo Han Guowen Xu Yuanpu Zhou Xuehuan Yang Jiwei Li Tianwei Zhang AAML 30 43 0 02 Mar 2022
A Survey of Neural Trojan Attacks and Defenses in Deep Learning Jie Wang Ghulam Mubashar Hassan Naveed Akhtar AAML 31 24 0 15 Feb 2022
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training Zhenting Wang Hailun Ding Juan Zhai Shiqing Ma AAML 15 45 0 13 Feb 2022
Jigsaw Puzzle: Selective Backdoor Attack to Subvert Malware Classifiers Limin Yang Zhi Chen Jacopo Cortellazzi Feargus Pendlebury Kevin Tu Fabio Pierazzi Lorenzo Cavallaro Gang Wang AAML 18 36 0 11 Feb 2022
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire Siddhartha Datta N. Shadbolt AAML 29 7 0 28 Jan 2022
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World Hua Ma Yinshan Li Yansong Gao A. Abuadbba Zhi-Li Zhang Anmin Fu Hyoungshick Kim S. Al-Sarawi N. Surya Derek Abbott 21 34 0 21 Jan 2022
Distributed Machine Learning and the Semblance of Trust Dmitrii Usynin Alexander Ziller Daniel Rueckert Jonathan Passerat-Palmbach Georgios Kaissis 18 1 0 21 Dec 2021
Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures Eugene Bagdasaryan Vitaly Shmatikov SILM AAML 27 76 0 09 Dec 2021
Defending against Model Stealing via Verifying Embedded External Features Yiming Li Linghui Zhu Xiaojun Jia Yong Jiang Shutao Xia Xiaochun Cao AAML 43 61 0 07 Dec 2021
TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems Bao Gia Doan Minhui Xue Shiqing Ma Ehsan Abbasnejad D. Ranasinghe AAML 41 53 0 19 Nov 2021
Don't Knock! Rowhammer at the Backdoor of DNN Models M. Tol Saad Islam Andrew J. Adiletta B. Sunar Ziming Zhang AAML 27 15 0 14 Oct 2021
Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks Shawn Shan A. Bhagoji Haitao Zheng Ben Y. Zhao AAML 91 50 0 13 Oct 2021
Widen The Backdoor To Let More Attackers In Siddhartha Datta Giulio Lovisotto Ivan Martinovic N. Shadbolt AAML 13 3 0 09 Oct 2021
Adversarial Unlearning of Backdoors via Implicit Hypergradient Yi Zeng Si-An Chen Won Park Z. Morley Mao Ming Jin R. Jia AAML 25 172 0 07 Oct 2021
Unsolved Problems in ML Safety Dan Hendrycks Nicholas Carlini John Schulman Jacob Steinhardt 186 273 0 28 Sep 2021
Certifiers Make Neural Networks Vulnerable to Availability Attacks Tobias Lorenz M. Kwiatkowska Mario Fritz AAML SILM 12 2 0 25 Aug 2021
TRAPDOOR: Repurposing backdoors to detect dataset bias in machine learning-based genomic analysis Esha Sarkar Michail Maniatakos 29 3 0 14 Aug 2021
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning Jinyuan Jia Yupei Liu Neil Zhenqiang Gong SILM SSL 24 151 0 01 Aug 2021
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers Stefanos Koffas Jing Xu Mauro Conti S. Picek AAML 17 66 0 30 Jul 2021
Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness Yuwei Sun H. Ochiai Hiroshi Esaki FedML 74 45 0 30 Jul 2021
Spinning Sequence-to-Sequence Models with Meta-Backdoors Eugene Bagdasaryan Vitaly Shmatikov SILM AAML 38 8 0 22 Jul 2021
The Threat of Offensive AI to Organizations Yisroel Mirsky Ambra Demontis J. Kotak Ram Shankar Deng Gelei Liu Yang Xinming Zhang Wenke Lee Yuval Elovici Battista Biggio 33 81 0 30 Jun 2021
Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers C. Ashcraft Kiran Karra 15 22 0 14 Jun 2021
Handcrafted Backdoors in Deep Neural Networks Sanghyun Hong Nicholas Carlini Alexey Kurakin 19 71 0 08 Jun 2021
RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things Huming Qiu Hua Ma Zhi-Li Zhang Yifeng Zheng Anmin Fu Pan Zhou Yansong Gao Derek Abbott S. Al-Sarawi MQ 19 9 0 09 May 2021
Hidden Backdoors in Human-Centric Language Models Shaofeng Li Hui Liu Tian Dong Benjamin Zi Hao Zhao Minhui Xue Haojin Zhu Jialiang Lu SILM 27 143 0 01 May 2021
Stealthy Backdoors as Compression Artifacts Yulong Tian Fnu Suya Fengyuan Xu David E. Evans 27 22 0 30 Apr 2021
Robust Backdoor Attacks against Deep Neural Networks in Real Physical World Mingfu Xue Can He Shichang Sun Jian Wang Weiqiang Liu AAML 31 43 0 15 Apr 2021
PointBA: Towards Backdoor Attacks in 3D Point Cloud Xinke Li Zhirui Chen Yue Zhao Zekun Tong Yabang Zhao A. Lim Qiufeng Wang 3DPC AAML 60 51 0 30 Mar 2021
MISA: Online Defense of Trojaned Models using Misattributions Panagiota Kiourti Wenchao Li Anirban Roy Karan Sikka Susmit Jha 13 10 0 29 Mar 2021
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry Yingqi Liu Guangyu Shen Guanhong Tao Zhenting Wang Shiqing Ma Xinming Zhang AAML 24 8 0 16 Mar 2021
A Real-time Defense against Website Fingerprinting Attacks Shawn Shan A. Bhagoji Haitao Zheng Ben Y. Zhao AAML 14 19 0 08 Feb 2021
Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks Zhengyan Zhang Guangxuan Xiao Yongwei Li Tian Lv Fanchao Qi Zhiyuan Liu Yasheng Wang Xin Jiang Maosong Sun AAML 23 67 0 18 Jan 2021
Explainability Matters: Backdoor Attacks on Medical Imaging Munachiso Nwadike Takumi Miyawaki Esha Sarkar Michail Maniatakos Farah E. Shamout AAML 16 13 0 30 Dec 2020
TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors Ren Pang Zheng-Wei Zhang Xiangshan Gao Zhaohan Xi S. Ji Peng Cheng Xiapu Luo Ting Wang AAML 29 31 0 16 Dec 2020