Authors

* External authors

Venue

Date

Share

LOCKEY: A Novel Approach to Model Authentication and Deepfake Tracking

Mayank Kumar Singh*

Naoya Takahashi

Wei-Hsiang Liao

Yuki Mitsufuji

* External authors

NeurIPS 2024

2025

Abstract

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.

Related Publications

Theory-Informed Improvements to Classifier-Free Guidance for Discrete Diffusion Models

ICLR, 2026
Kevin Rojas, Ye He, Chieh-Hsin Lai, Yuhta Takida, Yuki Mitsufuji, Molei Tao

Classifier-Free Guidance (CFG) is a widely used technique for conditional generation and improving sample quality in continuous diffusion models, and recent works have extended it to discrete diffusion. This paper theoretically analyzes CFG in the context of masked discrete …

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

ICLR, 2026
Joungbin Lee, Jaewoo Jung, Jisang Han, Takuya Narihira, Kazumi Fukuda, Junyoung Seo, Sunghwan Hong, Yuki Mitsufuji, Seungryong Kim*

We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we employ dual spatio-temporal conditio…

LLM2Fx-Tools: Tool Calling For Music Post-Production

ICLR, 2026
Seungheon Doh, Junghyun Koo*, Marco A. Martínez-Ramírez, Woosung Choi, Wei-Hsiang Liao, Qiyu Wu, Juhan Nam, Yuki Mitsufuji

This paper introduces LLM2Fx-Tools, a multimodal tool-calling framework that generates executable sequences of audio effects (Fx-chain) for music post-production. LLM2Fx-Tools uses a large language model (LLM) to understand audio inputs, select audio effects types, determine…

  • HOME
  • Publications
  • LOCKEY: A Novel Approach to Model Authentication and Deepfake Tracking

JOIN US

Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.