all InfoSec news
Towards Better Statistical Understanding of Watermarking LLMs
March 21, 2024, 4:10 a.m. | Zhongze Cai, Shang Liu, Hanzhao Wang, Huaiyang Zhong, Xiaocheng Li
cs.CR updates on arXiv.org arxiv.org
Abstract: In this paper, we study the problem of watermarking large language models (LLMs). We consider the trade-off between model distortion and detection ability and formulate it as a constrained optimization problem based on the green-red algorithm of Kirchenbauer et al. (2023a). We show that the optimal solution to the optimization problem enjoys a nice analytical property which provides a better understanding and inspires the algorithm design for the watermarking process. We develop an online dual …
algorithm arxiv cs.cr cs.it cs.lg detection green language language models large llms math.it optimization problem solution stat.ml study trade understanding watermarking
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
1 day, 10 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
1 day, 10 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
1 day, 10 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Open-Source Intelligence (OSINT) Policy Analyst (TS/SCI)
@ WWC Global | Reston, Virginia, United States
Security Architect (DevSecOps)
@ EUROPEAN DYNAMICS | Brussels, Brussels, Belgium
Infrastructure Security Architect
@ Ørsted | Kuala Lumpur, MY
Contract Penetration Tester
@ Evolve Security | United States - Remote
Senior Penetration Tester
@ DigitalOcean | Canada