LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators

You Li, Guannan Zhao, Yuhao Ju, Yunqi He, Jie Gu +1 more
12/26/2025
cs.CRcs.AIcs.LG

No confident code implementation found for this paper.

Abstract

We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model corruption, and information leakage. On the software side, it embeds key bits into neurons that can trigger outliers to degrade performance and applies invariance transformations to obscure the key values. On the hardware side, it integrates a lightweight locking module into the AI accelerator while maintaining compatibility with various dataflow patterns and toolchains. An accelerator with a pre-stored secret key acts as a license to access the model services provided by the IP owner. The evaluation results show that LLA can withstand a broad range of oracle-guided key optimization attacks, while incurring a minimal computational overhead of less than 0.1% for 7,168 key bits.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Accelerators

84% match2025

Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems

84% match2026

STACK: Adversarial Attacks on LLM Safeguard Pipelines

83% match2025

Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMs

83% match2025

Locking Machine Learning Models into Hardware

83% match2024

Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks

82% match2023

Cite this paper

@article{li2025lla,
  title  = {LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators},
  author = {You Li and Guannan Zhao and Yuhao Ju and Yunqi He and Jie Gu and Hai Zhou},
  year   = {2025},
  eprint = {2512.22307},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.22307v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.22307.svg)](https://codeofpaper.com/paper/2512.22307)

Discussion