Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning

14 January 2020

Papers citing "Humpty Dumpty: Controlling Word Meanings via Corpus Poisoning"

24 / 24 papers shown

Title
Rethinking Membership Inference Attacks Against Transfer Learning Yanwei Yue Jing Chen Qianru Fang Kun He Ziming Zhao Hao Ren Guowen Xu Yang Liu Yang Xiang 145 36 0 20 Jan 2025
Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs Javier Rando Francesco Croce Kryvstof Mitka Stepan Shabalin Maksym Andriushchenko Nicolas Flammarion F. Tramèr 90 17 0 22 Apr 2024
Data Poisoning for In-context Learning Pengfei He Han Xu Yue Xing Hui Liu Makoto Yamada Jiliang Tang SILM AAML 100 13 0 03 Feb 2024
Manipulating Predictions over Discrete Inputs in Machine Teaching Xiaodong Wu Yufei Han H. Dahrouj Jianbing Ni Zhenwen Liang Xiangliang Zhang 71 0 0 31 Jan 2024
Universal Jailbreak Backdoors from Poisoned Human Feedback Javier Rando Florian Tramèr 121 75 0 24 Nov 2023
Poisoning Retrieval Corpora by Injecting Adversarial Passages Zexuan Zhong Ziqing Huang Alexander Wettig Danqi Chen AAML 129 76 0 29 Oct 2023
Dropout Attacks Andrew Yuan Alina Oprea Cheng Tan 57 0 0 04 Sep 2023
Manipulating Transfer Learning for Property Inference Yulong Tian Fnu Suya Anshuman Suri Fengyuan Xu David Evans AAML 70 6 0 21 Mar 2023
"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice Giovanni Apruzzese Hyrum S. Anderson Savino Dambra D. Freeman Fabio Pierazzi Kevin A. Roundy AAML 109 81 0 29 Dec 2022
Learned-Database Systems Security R. Schuster Jinyi Zhou Thorsten Eisenhofer Paul Grubbs Nicolas Papernot AAML 148 2 0 20 Dec 2022
An Input-Aware Mimic Defense Theory and its Practice Jiale Fu Yali Yuan Jiajun He Sichu Liang Zhe Huang Hongyu Zhu AAML 60 0 0 22 Aug 2022
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning Hongbin Liu Jinyuan Jia Neil Zhenqiang Gong 69 36 0 13 May 2022
Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures Eugene Bagdasaryan Vitaly Shmatikov SILM AAML 115 84 0 09 Dec 2021
Attacks against Ranking Algorithms with Text Embeddings: a Case Study on Recruitment Algorithms A. Samadi Debapriya Banerjee Shirin Nilizadeh 60 1 0 12 Aug 2021
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models Wenkai Yang Lei Li Zhiyuan Zhang Xuancheng Ren Xu Sun Bin He SILM 111 153 0 29 Mar 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 174 74 0 18 Jan 2021
TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors Ren Pang Zheng Zhang Xiangshan Gao Zhaohan Xi S. Ji Peng Cheng Xiapu Luo Ting Wang AAML 98 32 0 16 Dec 2020
A little goes a long way: Improving toxic language classification despite data scarcity Mika Juuti Tommi Gröndahl Adrian Flanagan Nirmal Asokan 94 25 0 25 Sep 2020
Trojaning Language Models for Fun and Profit Xinyang Zhang Zheng Zhang Shouling Ji Ting Wang SILM AAML 98 140 0 01 Aug 2020
Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review Yansong Gao Bao Gia Doan Zhi-Li Zhang Siqi Ma Jiliang Zhang Anmin Fu Surya Nepal Hyoungshick Kim AAML 129 235 0 21 Jul 2020
Cultural Cartography with Word Embeddings Dustin S. Stoltz Marshall A. Taylor 57 39 0 09 Jul 2020
You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion R. Schuster Congzheng Song Eran Tromer Vitaly Shmatikov SILM AAML 144 160 0 05 Jul 2020
Subpopulation Data Poisoning Attacks Matthew Jagielski Giorgio Severi Niklas Pousette Harger Alina Oprea AAML SILM 111 122 0 24 Jun 2020
Weight Poisoning Attacks on Pre-trained Models Keita Kurita Paul Michel Graham Neubig AAML SILM 152 458 0 14 Apr 2020