all InfoSec news
Differentially Private Next-Token Prediction of Large Language Models
March 26, 2024, 4:10 a.m. | James Flemings, Meisam Razaviyayn, Murali Annavaram
cs.CR updates on arXiv.org arxiv.org
Abstract: Ensuring the privacy of Large Language Models (LLMs) is becoming increasingly important. The most widely adopted technique to accomplish this is DP-SGD, which trains a model in such a way that guarantees Differential Privacy (DP). However, DP-SGD requires longer training times and larger memory requirements than SGD, while overestimating an adversary's capabilities in having white box access to the model. A more realistic scenario assumes only black-box access to a privacy-sensitive LLM. Motivated by these …
arxiv cs.cl cs.cr cs.lg differential privacy important language language models large llms memory next prediction privacy private requirements token training trains
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Social Engineer For Reverse Engineering Exploit Study
@ Independent study | Remote
SITEC- Systems Security Administrator- Camp HM Smith
@ Peraton | Camp H.M. Smith, HI, United States
Cyberspace Intelligence Analyst
@ Peraton | Fort Meade, MD, United States
General Manager, Cybersecurity, Google Public Sector
@ Google | Virginia, USA; United States
Cyber Security Advisor
@ H&M Group | Stockholm, Sweden
Engineering Team Manager – Security Controls
@ H&M Group | Stockholm, Sweden