AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

UniReFP: Robust Unified Fingerprinting for Vision Models against Cross-Task Repurposing Attacks

Ziye Geng, Guang Yang, Yihang Chen, Lingfeng Yao, Xing Shi, Miao Pan, Xin Fu, Changqing Luo

NeurIPS 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Identifies a cross-task model repurposing attack that breaks existing vision-model fingerprints and proposes UniReFP, a unified fingerprinting framework using class-level semantic evidence across tasks.

Problem

Existing model fingerprinting methods for vision models can be rendered inapplicable by cross-task model repurposing, where a model is modified to serve a different task.

Approach

A unified fingerprinting framework that embeds ownership evidence in a shared class-level semantic space so that it survives repurposing to different vision tasks.

Surprising findings

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy