paper-with-me

Papers

High-Robustness, Low-Transferability Fingerprinting of Neural Networks

2021-05-14 · Siyue Wang, Xiao Wang, Pin-Yu Chen, Pu Zhao, Xue Lin

This paper proposes Characteristic Examples for effectively fingerprinting deep neural networks, featuring high-robustness to the base model against model pruning as well as low-transferability to unassociated models. This is the first work taking both robustness and transferability into consideration for generating realistic fingerprints, whereas current methods lack practical assumptions and may incur large false positive rates. To achieve better trade-off between robustness and transferability, we propose three kinds of characteristic examples: vanilla C-examples, RC-examples, and LTRC-example, to derive fingerprints from the original base model. To fairly characterize the trade-off between robustness and transferability, we propose Uniqueness Score, a comprehensive metric that measures the difference between robustness and transferability, which also serves as an indicator to the false alarm problem.

📄 PDF Abstract BibTeX arXiv:2105.07078

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Are Robust LLM Fingerprints Adversarially Robust?

2025-09-30 · Anshul Nasery, Edoardo Contente, Alkin Kaz, Pramod Viswanath 외 arxiv

Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly focused on benign perturbations such as incremental fine-tuning, model m…

Adversarial Robustness

Efficient, Robust, and Anti-Collusion Fingerprinting of Image Diffusion Models

2026-06-11 · Jianwei Fei, Yunshu Dai, Zhihua Xia, Xiaochun Cao 외 arxiv

Model fingerprinting, embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect the intellectual property rights (IPR) of generative text-to-image (T…

Image Generation

Robust Neural Audio Fingerprinting using Music Foundation Models

2025-11-07 · Shubhr Singh, Kiran Bhat, Xavier Riley, Benjamin Resnick 외 arxiv

The proliferation of distorted, compressed, and manipulated music on modern media platforms like TikTok motivates the development of more robust audio fingerprinting techniques to identify the sources of musical recordin…

Data Augmentation

Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

2026-05-18 · Sixu Chen, Xiang Chen, Hongyao Yu, Jiaxin Hong 외 arxiv

The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing LLM fingerprinting methods, particularly active approaches that embed …

Deep-Learning-Based Device Fingerprinting for Increased LoRa-IoT Security: Sensitivity to Network Deployment Changes

2022-08-31 · Bechir Hamdaoui, Abdurrahman Elmaghbub

Deep-learning-based device fingerprinting has recently been recognized as a key enabler for automated network access authentication. Its robustness to impersonation attacks due to the inherent difficulty of replicating p…

Sensitivity