PulseAugur
EN
LIVE 09:02:22

New NWaaS system offers non-intrusive IP protection for ML models

By PulseAugur Editorial · [1 sources] ·

Researchers have developed NWaaS, a novel system designed to protect intellectual property in Machine Learning as a Service (MaaS) environments. This system introduces ShadowMark, a watermarking algorithm that verifies ownership without altering the model's performance or requiring access to original training data. NWaaS also incorporates a collaborative partitioning mechanism for flexible cost-privacy trade-offs and a proportion disparity joint scheduling algorithm to optimize resource utilization in edge-cloud settings. AI

IMPACT Provides a new method for securing intellectual property in ML services without performance degradation.

RANK_REASON The cluster contains a research paper detailing a new system and algorithm. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New NWaaS system offers non-intrusive IP protection for ML models

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Haonan An, Qianyao Ren, Guang Hua, Tao Li, Yu Guo, Yanan Ma, Hangcheng Cao, Yuguang Fang ·

    NWaaS: A Non-Intrusive and Privacy-Preserving Watermarking-as-a-Service System with Adaptive Resource Scheduling

    arXiv:2507.18036v2 Announce Type: replace-cross Abstract: Securing intellectual property (IP) in Machine Learning as a Service is critical yet challenging. While deep neural network watermarking serves as a standard defense against model extraction, existing Watermarking-as-a-Ser…

RELATED TOPICS