all AI news
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
March 5, 2024, 2:43 p.m. | Anudeex Shetty, Yue Teng, Ke He, Qiongkai Xu
cs.LG updates on arXiv.org arxiv.org
Abstract: Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Processing (NLP). Prior studies have shown that EaaS can be prone to model extraction attacks; nevertheless, this concern could be mitigated by adding backdoor watermarks to the text embeddings and subsequently verifying the attack models post-publication. Through the analysis of the recent watermarking strategy for EaaS, EmbMarker, we design a novel …
abstract arxiv as-a-service attacks backdoor become capabilities copyright copyright protection cs.cl cs.cr cs.lg embedding extraction feature feature extraction language language processing natural natural language natural language processing nlp prior processing protection service solution studies tasks type watermarks
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US