# LOCKEY: A Novel Approach to Model Authentication and Deepfake Tracking

arXiv: https://arxiv.org/abs/2409.07743 · HTML: https://mlsanity.com/paper/2409.07743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 12 Sep 2024.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 18 of 18)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [Proactive Detection of Voice Cloning with Localized Watermarking](https://mlsanity.com/paper/2401.17264/) (2024)
- [WavMark: Watermarking for Audio Generation](https://mlsanity.com/paper/2308.12770/) (2023)
- [Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Models](https://mlsanity.com/paper/2303.00608/) (2023)
- [SilentCipher: Deep Audio Watermarking](https://mlsanity.com/paper/2406.03822/) (2024)
- [Latent Watermarking of Audio Generative Models](https://mlsanity.com/paper/2409.02915/) (2024)
- [Collaborative Watermarking for Adversarial Speech Synthesis](https://mlsanity.com/paper/2309.15224/) (2023)
- [Robust One-Shot Singing Voice Conversion](https://mlsanity.com/paper/2210.11096/) (2022)
- [Source Mixing and Separation Robust Audio Steganography](https://mlsanity.com/paper/2110.05054/) (2021)
- [Iteratively Improving Speech Recognition and Voice Conversion](https://mlsanity.com/paper/2305.15055/) (2023)

## Abstract (arXiv)

This paper presents a novel approach to deter unauthorized deepfakes and enable user tracking in generative models, even when the user has full access to the model parameters, by integrating key-based model authentication with watermarking techniques. Our method involves providing users with model parameters accompanied by a unique, user-specific key. During inference, the model is conditioned upon the key along with the standard input. A valid key results in the expected output, while an invalid key triggers a degraded output, thereby enforcing key-based model authentication. For user tracking, the model embeds the user's unique key as a watermark within the generated content, facilitating the identification of the user's ID. We demonstrate the effectiveness of our approach on two types of models, audio codecs and vocoders, utilizing the SilentCipher watermarking method. Additionally, we assess the robustness of the embedded watermarks against various distortions, validating their reliability in various scenarios.