Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

18 December 2020

Chulin Xie

Papers citing "Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses"

48 / 148 papers shown

Title
Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario Pedro Miguel Sánchez Sánchez Alberto Huertas Celdrán Enrique Tomás Martínez Beltrán Daniel Demeter Gérome Bovet Gregorio Martínez Pérez Burkhard Stiller AAML FedML 27 6 0 20 Oct 2022
Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning Yuxin Wen Jonas Geiping Liam H. Fowl Hossein Souri Ramalingam Chellappa Micah Goldblum Tom Goldstein AAML SILM FedML 30 9 0 17 Oct 2022
Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networks Run Wang Jixing Ren Boheng Li Tianyi She Wenhui Zhang Liming Fang Jing Chen Chao Shen Lina Wang WIGM 32 16 0 14 Oct 2022
COLLIDER: A Robust Training Framework for Backdoor Data H. M. Dolatabadi S. Erfani C. Leckie AAML 17 7 0 13 Oct 2022
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning? Yi Zeng Minzhou Pan Himanshu Jahagirdar Ming Jin Lingjuan Lyu R. Jia AAML 39 21 0 12 Oct 2022
Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System A. Shahid Ahmed Imteaj Peter Y. Wu Diane A. Igoche Tauhidul Alam AAML 11 9 0 17 Aug 2022
Lethal Dose Conjecture on Data Poisoning Wenxiao Wang Alexander Levine S. Feizi FedML 13 15 0 05 Aug 2022
Holistic Robust Data-Driven Decisions Amine Bennouna Bart P. G. Van Parys Ryan Lucas OOD 36 21 0 19 Jul 2022
Security and Safety Aspects of AI in Industry Applications H. D. Doran 14 0 0 16 Jul 2022
Neurotoxin: Durable Backdoors in Federated Learning Zhengming Zhang Ashwinee Panda Linyue Song Yaoqing Yang Michael W. Mahoney Joseph E. Gonzalez Kannan Ramchandran Prateek Mittal FedML 29 130 0 12 Jun 2022
Autoregressive Perturbations for Data Poisoning Pedro Sandoval-Segura Vasu Singla Jonas Geiping Micah Goldblum Tom Goldstein David Jacobs AAML 25 40 0 08 Jun 2022
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free Tianlong Chen Zhenyu (Allen) Zhang Yihua Zhang Shiyu Chang Sijia Liu Zhangyang Wang AAML 46 25 0 24 May 2022
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning Antonio Emanuele Cinà Kathrin Grosse Ambra Demontis Sebastiano Vascon Werner Zellinger Bernhard A. Moser Alina Oprea Battista Biggio Marcello Pelillo Fabio Roli AAML 22 116 0 04 May 2022
Indiscriminate Data Poisoning Attacks on Neural Networks Yiwei Lu Gautam Kamath Yaoliang Yu AAML 43 24 0 19 Apr 2022
Poisons that are learned faster are more effective Pedro Sandoval-Segura Vasu Singla Liam H. Fowl Jonas Geiping Micah Goldblum David Jacobs Tom Goldstein 6 17 0 19 Apr 2022
Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures Huming Qiu Hua Ma Zhi-Li Zhang A. Abuadbba Wei Kang Anmin Fu Yansong Gao ELM AAML 23 15 0 13 Apr 2022
Energy-Latency Attacks via Sponge Poisoning Antonio Emanuele Cinà Ambra Demontis Battista Biggio Fabio Roli Marcello Pelillo SILM 47 29 0 14 Mar 2022
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice Andreas Grivas Nikolay Bogoychev Adam Lopez 13 9 0 12 Mar 2022
On the Effectiveness of Adversarial Training against Backdoor Attacks Yinghua Gao Dongxian Wu Jingfeng Zhang Guanhao Gan Shutao Xia Gang Niu Masashi Sugiyama AAML 32 22 0 22 Feb 2022
Identifying Backdoor Attacks in Federated Learning via Anomaly Detection Yuxi Mi Yiheng Sun Jihong Guan Shuigeng Zhou AAML FedML 11 1 0 09 Feb 2022
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation Wenxiao Wang Alexander Levine S. Feizi AAML 20 60 0 05 Feb 2022
Can Adversarial Training Be Manipulated By Non-Robust Features? Lue Tao Lei Feng Hongxin Wei Jinfeng Yi Sheng-Jun Huang Songcan Chen AAML 81 16 0 31 Jan 2022
Security for Machine Learning-based Software Systems: a survey of threats, practices and challenges Huaming Chen Muhammad Ali Babar AAML 37 21 0 12 Jan 2022
On the Security & Privacy in Federated Learning Gorka Abad S. Picek Víctor Julio Ramírez-Durán A. Urbieta 44 11 0 10 Dec 2021
Availability Attacks Create Shortcuts Da Yu Huishuai Zhang Wei Chen Jian Yin Tie-Yan Liu AAML 31 57 0 01 Nov 2021
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models Kangjie Chen Yuxian Meng Xiaofei Sun Shangwei Guo Tianwei Zhang Jiwei Li Chun Fan SILM 23 106 0 06 Oct 2021
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings Mazda Moayeri S. Feizi AAML 21 19 0 30 Aug 2021
Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning Virat Shejwalkar Amir Houmansadr Peter Kairouz Daniel Ramage AAML 34 213 0 23 Aug 2021
Evaluating Large Language Models Trained on Code Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Pondé ... Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever Wojciech Zaremba ELM ALM 78 5,055 0 07 Jul 2021
Adversarial Examples Make Strong Poisons Liam H. Fowl Micah Goldblum Ping Yeh-Chiang Jonas Geiping Wojtek Czaja Tom Goldstein SILM 26 132 0 21 Jun 2021
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch Hossein Souri Liam H. Fowl Ramalingam Chellappa Micah Goldblum Tom Goldstein SILM 31 123 0 16 Jun 2021
Turning Federated Learning Systems Into Covert Channels Gabriele Costa Fabio Pinelli S. Soderi Gabriele Tolomei FedML 37 10 0 21 Apr 2021
SGBA: A Stealthy Scapegoat Backdoor Attack against Deep Neural Networks Yingzhe He Zhili Shen Chang Xia Jingyu Hua Wei Tong Sheng Zhong AAML 8 6 0 02 Apr 2021
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations Eitan Borgnia Jonas Geiping Valeriia Cherepanova Liam H. Fowl Arjun Gupta Amin Ghiasi Furong Huang Micah Goldblum Tom Goldstein 32 46 0 02 Mar 2021
What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning Jonas Geiping Liam H. Fowl Gowthami Somepalli Micah Goldblum Michael Moeller Tom Goldstein TDI AAML SILM 27 40 0 26 Feb 2021
Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release Liam H. Fowl Ping Yeh-Chiang Micah Goldblum Jonas Geiping Arpit Bansal W. Czaja Tom Goldstein 16 43 0 16 Feb 2021
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training Lue Tao Lei Feng Jinfeng Yi Sheng-Jun Huang Songcan Chen AAML 34 71 0 09 Feb 2021
Unlearnable Examples: Making Personal Data Unexploitable Hanxun Huang Xingjun Ma S. Erfani James Bailey Yisen Wang MIACV 156 190 0 13 Jan 2021
With False Friends Like These, Who Can Notice Mistakes? Lue Tao Lei Feng Jinfeng Yi Songcan Chen AAML 13 5 0 29 Dec 2020
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff Eitan Borgnia Valeriia Cherepanova Liam H. Fowl Amin Ghiasi Jonas Geiping Micah Goldblum Tom Goldstein Arjun Gupta AAML 6 127 0 18 Nov 2020
Concealed Data Poisoning Attacks on NLP Models Eric Wallace Tony Zhao Shi Feng Sameer Singh SILM 19 18 0 23 Oct 2020
VenoMave: Targeted Poisoning Against Speech Recognition H. Aghakhani Lea Schonherr Thorsten Eisenhofer D. Kolossa Thorsten Holz Christopher Kruegel Giovanni Vigna AAML 8 17 0 21 Oct 2020
Backdoor Learning: A Survey Yiming Li Yong Jiang Zhifeng Li Shutao Xia AAML 45 586 0 17 Jul 2020
Backdoors in Neural Models of Source Code Goutham Ramakrishnan Aws Albarghouthi AAML SILM 28 56 0 11 Jun 2020
Threats to Federated Learning: A Survey Lingjuan Lyu Han Yu Qiang Yang FedML 202 434 0 04 Mar 2020
Model-Reuse Attacks on Deep Learning Systems Yujie Ji Xinyang Zhang S. Ji Xiapu Luo Ting Wang SILM AAML 134 186 0 02 Dec 2018
SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems Edward Chou Florian Tramèr Giancarlo Pellegrino AAML 168 287 0 02 Dec 2018
Analyzing Federated Learning through an Adversarial Lens A. Bhagoji Supriyo Chakraborty Prateek Mittal S. Calo FedML 191 1,032 0 29 Nov 2018