all InfoSec news
Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness. (arXiv:2205.10159v1 [cs.CR])
May 23, 2022, 1:20 a.m. | Jiankai Jin, Olga Ohrimenko, Benjamin I. P. Rubinstein
cs.CR updates on arXiv.org arxiv.org
Adversarial examples pose a security risk as they can alter a classifier's
decision through slight perturbations to a benign input. Certified robustness
has been proposed as a mitigation strategy where given an input $x$, a
classifier returns a prediction and a radius with a provable guarantee that any
perturbation to $x$ within this radius (e.g., under the $L_2$ norm) will not
alter the classifier's prediction. In this work, we show that these guarantees
can be invalidated due to limitations of …
More from arxiv.org / cs.CR updates on arXiv.org
One-shot Empirical Privacy Estimation for Federated Learning
1 day, 9 hours ago |
arxiv.org
Transferability Ranking of Adversarial Examples
1 day, 9 hours ago |
arxiv.org
A survey on hardware-based malware detection approaches
1 day, 9 hours ago |
arxiv.org
Explainable Ponzi Schemes Detection on Ethereum
1 day, 9 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