all InfoSec news
Pandora's White-Box: Increased Training Data Leakage in Open LLMs
Feb. 28, 2024, 5:11 a.m. | Jeffrey G. Wang, Jason Wang, Marvin Li, Seth Neel
cs.CR updates on arXiv.org arxiv.org
Abstract: In this paper we undertake a systematic study of privacy attacks against open source Large Language Models (LLMs), where an adversary has access to either the model weights, gradients, or losses, and tries to exploit them to learn something about the underlying training data. Our headline results are the first membership inference attacks (MIAs) against pre-trained LLMs that are able to simultaneously achieve high TPRs and low FPRs, and a pipeline showing that over $50\%$ …
access adversary arxiv attacks box cs.ai cs.cr cs.lg data data leakage exploit language language models large learn llms losses open source pandora privacy study training training data
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
1 day, 12 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
1 day, 12 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
1 day, 12 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Principal Security Analyst - Threat Labs (Position located in India) (Remote)
@ KnowBe4, Inc. | Kochi, India
Cyber Security - Cloud Security and Security Architecture - Manager - Multiple Positions - 1500860
@ EY | Dallas, TX, US, 75219
Enterprise Security Architect (Intermediate)
@ Federal Reserve System | Remote - Virginia
Engineering -- Tech Risk -- Global Cyber Defense & Intelligence -- Associate -- Dallas
@ Goldman Sachs | Dallas, Texas, United States
Vulnerability Management Team Lead - North Central region (Remote)
@ GuidePoint Security LLC | Remote in the United States