30 citations · 77 across the 7 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 3 cited
Membership Inference Attacks on DNNs using Adversarial Perturbations
Hassan Ali, Adnan Qayyum, Ala Al-Fuqaha +1
Several membership inference (MI) attacks have been proposed to audit a target DNN. Given a set of subjects, MI attacks tell which subjects the target DNN has seen during training.…
cs.LG2023★ 3 cited
Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models
Hassan Ali, Muhammad Atif Butt, Fethi Filali +2
Recent works have shown that deep learning (DL) models can effectively learn city-wide crowd-flow patterns, which can be used for more effective urban planning and smart city manag…