all InfoSec news
A Semantic Invariant Robust Watermark for Large Language Models
March 1, 2024, 5:11 a.m. | Aiwei Liu, Leyi Pan, Xuming Hu, Shiao Meng, Lijie Wen
cs.CR updates on arXiv.org arxiv.org
Abstract: Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each generation step. However, prior algorithms face a trade-off between attack robustness and security robustness. This is because the watermark logits for a token are determined by a certain number of preceding tokens; a small number leads to low security robustness, while a large …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Information Technology Security Engineer
@ Plexus Worldwide | Scottsdale, Arizona, United States
Principal Email Security Researcher (Cortex XDR)
@ Palo Alto Networks | Tel Aviv-Yafo, Israel
Lead Security Engineer - Cloud Security, AWS
@ JPMorgan Chase & Co. | Bengaluru, Karnataka, India