all InfoSec news
Publicly Detectable Watermarking for Language Models
Oct. 26, 2023, 12:54 p.m. |
IACR News www.iacr.org
ePrint Report: Publicly Detectable Watermarking for Language Models
Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang
We construct the first provable watermarking scheme for language models with public detectability or verifiability: we use a private key for watermarking and a public key for watermark detection. Our protocol is the first watermarking scheme that does not embed a statistical signal in generated text. Rather, we directly embed a publicly-verifiable cryptographic signature using a form of rejection sampling. …
detection eprint report key language language models private private key protocol public public key report wang watermarking
More from www.iacr.org / IACR News
Regev Factoring Beyond Fibonacci: Optimizing Prefactors
1 day, 20 hours ago |
www.iacr.org
NTRU-based FHE for Larger Key and Message Space
1 day, 20 hours ago |
www.iacr.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Senior Security Researcher, SIEM
@ Huntress | Remote Canada
Senior Application Security Engineer
@ Revinate | San Francisco Bay Area
Cyber Security Manager
@ American Express Global Business Travel | United States - New York - Virtual Location
Incident Responder Intern
@ Bentley Systems | Remote, PA, US
SC2024-003533 Senior Online Vulnerability Assessment Analyst (CTS) - THU 9 May
@ EMW, Inc. | Mons, Wallonia, Belgium