# StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning

arXiv: https://arxiv.org/abs/2201.05889 · HTML: https://mlsanity.com/paper/2201.05889/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 65 references that are in the map.
- First posted on arXiv 15 Jan 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [Knockoff Nets: Stealing Functionality of Black-Box Models](https://mlsanity.com/paper/1812.02766/) (2018)
- [High Accuracy and High Fidelity Extraction of Neural Networks](https://mlsanity.com/paper/1909.01838/) (2019)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [PRADA: Protecting against DNN Model Stealing Attacks](https://mlsanity.com/paper/1805.02628/) (2018)
- [Poisoning and Backdooring Contrastive Learning](https://mlsanity.com/paper/2106.09667/) (2021)
- [Entangled Watermarks as a Defense against Model Extraction](https://mlsanity.com/paper/2002.12200/) (2020)
- [Thieves on Sesame Street! Model Extraction of BERT-based APIs](https://mlsanity.com/paper/1910.12366/) (2019)
- [Data-Free Model Extraction](https://mlsanity.com/paper/2011.14779/) (2020)
- [BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning](https://mlsanity.com/paper/2108.00352/) (2021)
- [Stealing Hyperparameters in Machine Learning](https://mlsanity.com/paper/1802.05351/) (2018)
- [Stealing Links from Graph Neural Networks](https://mlsanity.com/paper/2005.02131/) (2020)
- [MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation](https://mlsanity.com/paper/2005.03161/) (2020)

## Built on by (most cited first, 23 of 23)

- [I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences](https://mlsanity.com/paper/2206.08451/) (2022)
- [Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders](https://mlsanity.com/paper/2201.07513/) (2022)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [MEA-Defender: A Robust Watermark against Model Extraction Attack](https://mlsanity.com/paper/2401.15239/) (2024)
- [A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability](https://mlsanity.com/paper/2404.02462/) (2024)
- [Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders](https://mlsanity.com/paper/2310.08571/) (2023)
- [ModelShield: Adaptive and Robust Watermark against Model Extraction Attack](https://mlsanity.com/paper/2405.02365/) (2024)
- [Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems](https://mlsanity.com/paper/2311.11796/) (2023)
- [REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service](https://mlsanity.com/paper/2301.02905/) (2023)
- [Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2601.15678/) (2026)
- [Examining the Threat Landscape: Foundation Models and Model Stealing](https://mlsanity.com/paper/2502.18077/) (2025)
- [ADAGE: Active Defenses Against GNN Extraction](https://mlsanity.com/paper/2503.00065/) (2025)
- [BESA: Boosting Encoder Stealing Attack with Perturbation Recovery](https://mlsanity.com/paper/2506.04556/) (2025)
- [Dataset Ownership Verification for Pre-trained Masked Models](https://mlsanity.com/paper/2507.12022/) (2025)
- [Steal the Patch Size: Adversarially Manipulate Vision-Language Models](https://mlsanity.com/paper/2607.00174/) (2026)
- [SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning](https://mlsanity.com/paper/2308.04673/) (2023)
- [Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction](https://mlsanity.com/paper/2312.00855/) (2023)
- [Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them](https://mlsanity.com/paper/2401.11723/) (2024)
- [Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services](https://mlsanity.com/paper/2408.02814/) (2024)
- [Rotation, Scale, and Translation Resilient Black-box Fingerprinting for Intellectual Property Protection of EaaS Models](https://mlsanity.com/paper/2510.16706/) (2025)
- [ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders](https://mlsanity.com/paper/2604.22550/) (2026)
- [JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols](https://mlsanity.com/paper/2608.26982/) (2026)
- [Steal the Knowledge, Inherit the Mark: TwinMark for Distillation Watermarking via Second Moments and Class Multiplexing](https://mlsanity.com/paper/2609.19011/) (2026)

## Abstract (arXiv)

Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective encoders using a large volume of unlabeled data, leading to the emerging encoder as a service (EaaS). A pre-trained encoder may be deemed confidential because its training requires lots of data and computation resources as well as its public release may facilitate misuse of AI, e.g., for deepfakes generation. In this paper, we propose the first attack called StolenEncoder to steal pre-trained image encoders. We evaluate StolenEncoder on multiple target encoders pre-trained by ourselves and three real-world target encoders including the ImageNet encoder pre-trained by Google, CLIP encoder pre-trained by OpenAI, and Clarifai's General Embedding encoder deployed as a paid EaaS. Our results show that our stolen encoders have similar functionality with the target encoders. In particular, the downstream classifiers built upon a target encoder and a stolen one have similar accuracy. Moreover, stealing a target encoder using StolenEncoder requires much less data and computation resources than pre-training it from scratch. We also explore three defenses that perturb feature vectors produced by a target encoder. Our results show these defenses are not enough to mitigate StolenEncoder.