Name: DSPLab@UMich-Dearborn
Type: User
Company: University of Michigan, Dearborn
Bio: The Data-driven Security & Privacy Lab @ the University of Michigan, Dearborn. Research: trustworthy ML, cybercrime analysis, and cyber threat intelligence
Twitter: UM_DSPLAB
Location: Dearborn, MI
Blog: https://um-dsp.github.io/
DSPLab@UMich-Dearborn's Projects
A detection-resistant probing system for evasion of Internet censorship
DP-UTIL: A Comprehensive Utility Analysis of Differential Privacy in Machine Learning
Explanation-guided boosting of machine learning evasion attacks.
Open-source code analysis platform for C/C++/Java/Binary/Javascript/Python/Kotlin based on code property graphs. Discord https://discord.gg/vv4MH284Hc
Multi-faceted malware infection traffic characterization
Morphence: An implementation of a moving target defense against adversarial example attacks demonstrated for image classification models trained on MNIST and CIFAR10.
Autonomous Vehicle Risk Management Profile for Traffic Sign Recognition based on NIST AI RMF.
PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting
DSPLab@UMich-Dearborn Website