all InfoSec news
StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning. (arXiv:2201.05889v2 [cs.CR] UPDATED)
July 21, 2022, 1:20 a.m. | Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong
cs.CR updates on arXiv.org arxiv.org
Pre-trained encoders are general-purpose feature extractors that can be used
for many downstream tasks. Recent progress in self-supervised learning can
pre-train highly effective encoders using a large volume of unlabeled data,
leading to the emerging encoder as a service (EaaS). A pre-trained encoder may
be deemed confidential because its training requires lots of data and
computation resources as well as its public release may facilitate misuse of
AI, e.g., for deepfakes generation. In this paper, we propose the first attack …
More from arxiv.org / cs.CR updates on arXiv.org
One-shot Empirical Privacy Estimation for Federated Learning
1 day, 11 hours ago |
arxiv.org
Transferability Ranking of Adversarial Examples
1 day, 11 hours ago |
arxiv.org
A survey on hardware-based malware detection approaches
1 day, 11 hours ago |
arxiv.org
Explainable Ponzi Schemes Detection on Ethereum
1 day, 11 hours ago |
arxiv.org
Privacy-Preserving UCB Decision Process Verification via zk-SNARKs
1 day, 11 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineers
@ D. E. Shaw Research | New York City
Staff DFIR Investigator
@ SentinelOne | United States - Remote
Senior Consultant.e (H/F) - Product & Industrial Cybersecurity
@ Wavestone | Puteaux, France
Information Security Analyst
@ StarCompliance | York, United Kingdom, Hybrid
Senior Cyber Security Analyst (IAM)
@ New York Power Authority | White Plains, US