all InfoSec news
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing. (arXiv:2301.12554v2 [cs.LG] UPDATED)
May 24, 2023, 1:10 a.m. | Yatong Bai, Brendon G. Anderson, Aerin Kim, Somayeh Sojoudi
cs.CR updates on arXiv.org arxiv.org
While prior research has proposed a plethora of methods that enhance the
adversarial robustness of neural classifiers, practitioners are still reluctant
to adopt these techniques due to their unacceptably severe penalties in clean
accuracy. This paper shows that by mixing the output probabilities of a
standard classifier and a robust model, where the standard network is optimized
for clean accuracy and is not robust in general, this accuracy-robustness
trade-off can be significantly alleviated. We show that the robust base
classifier's …
accuracy adversarial penalties research robustness standard techniques trade
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Technology Specialist II: Network Architect
@ Los Angeles County Employees Retirement Association (LACERA) | Pasadena, CA
Cybersecurity Skills Challenge -- Sponsored by DoD
@ Correlation One | United States
Security Operations Center (SOC) Analyst
@ GK Cybersecurity Group | Remote
Cyber Threat Defense - PAM Manager
@ PwC | Amsterdam - Thomas R. Malthusstraat 5
InfoSec Specialist
@ Deutsche Bank | Bucharest
DevSecOps Engineer
@ Swiss Re | Bengaluru, KA, IN