all InfoSec news
Neural Network Trojans Analysis and Mitigation from the Input Domain. (arXiv:2202.06382v2 [cs.LG] UPDATED)
Feb. 17, 2022, 8:20 a.m. | Zhenting Wang, Hailun Ding, Juan Zhai, Shiqing Ma
cs.CR updates on arXiv.org arxiv.org
Deep Neural Networks (DNNs) can learn Trojans (or backdoors) from benign or
poisoned data, which raises security concerns of using them. By exploiting such
Trojans, the adversary can add a fixed input space perturbation to any given
input to mislead the model predicting certain outputs (i.e., target labels). In
this paper, we analyze such input space Trojans in DNNs, and propose a theory
to explain the relationship of a model's decision regions and Trojans: a
complete and accurate Trojan corresponds …
analysis domain input lg mitigation network neural network trojans
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Security Audit and Compliance Technical Analyst
@ Accenture Federal Services | Washington, DC
ICS Cyber Threat Intelligence Analyst
@ STEMBoard | Arlington, Virginia, United States
Cyber Operations Analyst
@ Peraton | Arlington, VA, United States
Cybersecurity – Information System Security Officer (ISSO)
@ Boeing | USA - Annapolis Junction, MD
Network Security Engineer I - Weekday Afternoons
@ Deepwatch | Remote