all InfoSec news
Differentially Private Image Classification from Features. (arXiv:2211.13403v1 [cs.LG])
Nov. 28, 2022, 2:10 a.m. | Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky
cs.CR updates on arXiv.org arxiv.org
Leveraging transfer learning has recently been shown to be an effective
strategy for training large models with Differential Privacy (DP). Moreover,
somewhat surprisingly, recent works have found that privately training just the
last layer of a pre-trained model provides the best utility with DP. While past
studies largely rely on algorithms like DP-SGD for training large models, in
the specific case of privately learning from features, we observe that
computational burden is low enough to allow for more sophisticated optimization …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Cybersecurity Skills Challenge -- Sponsored by DoD
@ Correlation One | United States
Security Operations Center (SOC) Analyst
@ GK Cybersecurity Group | Remote
Azure Security Architect
@ First Quality | Remote US - Eastern or Central Timezone
Senior Security Engineer
@ LRQA | Birmingham, GB, B37 7ES
Product Security Intern
@ Sinch | Chicago, Illinois, United States
Cyber Support Engineer
@ Darktrace | New York