On the Weaknesses of Backdoor-based Model Watermarking: An
Information-theoretic Perspective

On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective

10 September 2024

Aoting Hu

Papers citing "On the Weaknesses of Backdoor-based Model Watermarking: An Information-theoretic Perspective"

18 / 18 papers shown

Title
Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand Junfeng Guo Yiming Li Lixu Wang Shu-Tao Xia Heng-Chiao Huang Cong Liu Boheng Li 67 57 0 09 Oct 2023
Undetectable Watermarks for Language Models Miranda Christ Sam Gunn Or Zamir WaLM 54 140 0 25 May 2023
Reconstructive Neuron Pruning for Backdoor Defense Yige Li X. Lyu Xingjun Ma Nodens Koren Lingjuan Lyu Yue Liu Yugang Jiang AAML 58 44 0 24 May 2023
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection Kai Greshake Sahar Abdelnabi Shailesh Mishra C. Endres Thorsten Holz Mario Fritz SILM 120 489 0 23 Feb 2023
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations Zirui Peng Shaofeng Li Guoxing Chen Cheng Zhang Haojin Zhu Minhui Xue AAML FedML 55 68 0 17 Feb 2022
Defending against Model Stealing via Verifying Embedded External Features Yiming Li Linghui Zhu Xiaojun Jia Yong Jiang Shutao Xia Xiaochun Cao AAML 65 63 0 07 Dec 2021
Neural Approximate Sufficient Statistics for Implicit Models Yanzhi Chen Dinghuai Zhang Michael U. Gutmann Aaron Courville Zhanxing Zhu 389 84 0 20 Oct 2020
Backdoor Learning: A Survey Yiming Li Yong Jiang Zhifeng Li Shutao Xia AAML 101 603 0 17 Jul 2020
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data Ning Yu Vladislav Skripniuk Sahar Abdelnabi Mario Fritz WIGM 56 217 0 16 Jul 2020
Language Models are Few-Shot Learners Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan ... Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever Dario Amodei BDL 743 41,932 0 28 May 2020
A Simple Framework for Contrastive Learning of Visual Representations Ting-Li Chen Simon Kornblith Mohammad Norouzi Geoffrey E. Hinton SSL 358 18,752 0 13 Feb 2020
REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data Xinyun Chen Wenxiao Wang Chris Bender Yiming Ding R. Jia Yue Liu D. Song AAML 71 107 0 17 Nov 2019
Hidden Trigger Backdoor Attacks Aniruddha Saha Akshayvarun Subramanya Hamed Pirsiavash 81 623 0 30 Sep 2019
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding Jacob Devlin Ming-Wei Chang Kenton Lee Kristina Toutanova VLM SSL SSeg 1.7K 94,770 0 11 Oct 2018
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring Yossi Adi Carsten Baum Moustapha Cissé Benny Pinkas Joseph Keshet 61 677 0 13 Feb 2018
Embedding Watermarks into Deep Neural Networks Yusuke Uchida Yuki Nagai S. Sakazawa Shiníchi Satoh 122 607 0 15 Jan 2017
Membership Inference Attacks against Machine Learning Models Reza Shokri M. Stronati Congzheng Song Vitaly Shmatikov SLR MIALM MIACV 246 4,122 0 18 Oct 2016
Stealing Machine Learning Models via Prediction APIs Florian Tramèr Fan Zhang Ari Juels Michael K. Reiter Thomas Ristenpart SILM MLAU 104 1,805 0 09 Sep 2016