all InfoSec news
Teach LLMs to Phish: Stealing Private Information from Language Models
March 5, 2024, 3:11 p.m. | Ashwinee Panda, Christopher A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, Prateek Mittal
cs.CR updates on arXiv.org arxiv.org
Abstract: When large language models are trained on private data, it can be a significant privacy risk for them to memorize and regurgitate sensitive information. In this work, we propose a new practical data extraction attack that we call "neural phishing". This attack enables an adversary to target and extract sensitive or personally identifiable information (PII), e.g., credit card numbers, from a model trained on user data with upwards of 10% attack success rates, at times, …
adversary arxiv attack call can cs.ai cs.cl cs.cr cs.lg data extraction information language language models large llms phish phishing privacy privacy risk private private data risk sensitive sensitive information stealing teach work
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
2 days, 11 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
2 days, 11 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
2 days, 11 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Network Security Engineer
@ Meta | Menlo Park, CA | Remote, US
Security Engineer, Investigations - i3
@ Meta | Washington, DC
Threat Investigator- Security Analyst
@ Meta | Menlo Park, CA | Seattle, WA | Washington, DC
Security Operations Engineer II
@ Microsoft | Redmond, Washington, United States
Engineering -- Tech Risk -- Global Cyber Defense & Intelligence -- Bug Bounty -- Associate -- Dallas
@ Goldman Sachs | Dallas, Texas, United States