SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning
Not on the map. Why?
Abstract (arXiv)
Self-supervised learning (SSL), a paradigm harnessing unlabeled datasets to train robust encoders, has recently witnessed substantial success. These encoders serve as pivotal feature extractors for downstream tasks, demanding significant computational resources. Nevertheless, recent studies have shed light on vulnerabilities in pre-trained encoders, including backdoor and adversarial threats. Safeguarding the intellectual property of encoder trainers and ensuring the trustworthiness of deployed encoders pose notable challenges in SSL. To bridge these gaps, we introduce SSL-Auth, the first authentication framework designed explicitly for pre-trained encoders. SSL-Auth leverages selected key samples and employs a well-trained generative network to reconstruct watermark information, thus affirming the integrity of the encoder without compromising its performance. By comparing the reconstruction outcomes of the key samples, we can identify any malicious alterations. Comprehensive evaluations conducted on a range of encoders and diverse downstream tasks demonstrate the effectiveness of our proposed SSL-Auth.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 9 Aug 2023.
Builds on
27 of 44 references.
References · 27
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
- 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
- 2017Embedding Watermarks into Deep Neural Networkscited by 227
15 more
- 2021Poisoning and Backdooring Contrastive Learningcited by 149
- 2021BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learningcited by 120
- 2021Backdoor Attacks on Self-Supervised Learningcited by 89
- 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
- 2022SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoderscited by 43
- 2022Dataset Inference for Self-Supervised Modelscited by 36
- 2022Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoderscited by 30
- 2022On the Difficulty of Defending Self-Supervised Learning against Model Extractioncited by 22
- 2022StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learningcited by 21
- 2021Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authenticationcited by 17
- 2022Watermarking Pre-trained Encoders in Contrastive Learningcited by 10
- 2022SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learningcited by 9
- 2022ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Samplecited by 9
- 2022Neural network fragile watermarking with no model performance degradationcited by 7
- 2022AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learningcited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.