Abdullah Al-Dujaili

activity

20162019

most citedAdversarial Deep Learning for Robust Detection of Binary Encoded Malware

38 citations · 181 across the 15 of their papers we have counts for

collaborators

Showing 2019Show all

2 papers · 1 filter

cs.LG2019★ 18 cited

Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML

Sijia Liu, Songtao Lu, Xiangyi Chen +5

In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective fun…

cs.LG2019★ 14 cited

There are No Bit Parts for Sign Bits in Black-Box Attacks

Abdullah Al-Dujaili, Una-May O'Reilly

We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $ℓ_{\infty}$ and $ℓ_{2}$ metrics, where only l…