paper-with-me

Papers

Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign

2025-02-04 · Ruisi Zhang, Neusha Javidnia, Nojan Sheybani, Farinaz Koushanfar

This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software development. High-quality watermarks adhering to the detectability-fidelity-robustness tri-objective are limited due to codes' low-entropy nature. Watermark verification, however, often needs to reveal the signature and requires re-encoding new ones for code reuse, which potentially compromising the system's usability. To overcome these challenges, RoSeMary obtains high-quality watermarks by training the watermark insertion and extraction modules end-to-end to ensure (i) unaltered watermarked code functionality and (ii) enhanced detectability and robustness leveraging pre-trained CodeT5 as the insertion backbone to enlarge the code syntactic and variable rename transformation search space. In the deployment, RoSeMary uses zero-knowledge proofs for secure verification without revealing the underlying signatures. Extensive evaluations demonstrated RoSeMary achieves high detection accuracy while preserving the code functionality. RoSeMary is also robust against attacks and provides efficient secure watermark verification.

📄 PDF Abstract BibTeX arXiv:2502.02068

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks

2025-09-13 · Tong Zhou, Ruyi Ding, Gaowen Liu, Charles Fleming 외 arxiv

The rapid growth of digital and AI-generated images has amplified the need for secure and verifiable methods of image attribution. While digital watermarking offers more robust protection than metadata-based approaches--…

Image Attribution

ROSE: A RObust and SEcure DNN Watermarking

2022-06-22 · Kassem Kallas, Teddy Furon

Protecting the Intellectual Property rights of DNN models is of primary importance prior to their deployment. So far, the proposed methods either necessitate changes to internal model parameters or the machine learning p…

image-classificationImage Classification

ChainMarks: Securing DNN Watermark with Cryptographic Chain

2025-05-08 · Brian Choi, Shu Wang, Isabelle Choi, Kun Sun

With the widespread deployment of deep neural network (DNN) models, dynamic watermarking techniques are being used to protect the intellectual property of model owners. However, recent studies have shown that existing wa…

CIPHER: Cryptographic Insecurity Profiling via Hybrid Evaluation of Responses

2026-02-01 · Max Manolov, Tony Gao, Siddharth Shukla, Cheng-Ting Chou 외 arxiv

Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often contain exploitable flaws. Minor design choices (e.g., static initializati…

FreeMark: A Non-Invasive White-Box Watermarking for Deep Neural Networks

2024-09-16 · Yuzhang Chen, Jiangnan Zhu, Yujie Gu, Minoru Kuribayashi 외

Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection …