38 citations · 181 across the 15 of their papers we have counts for
15 papers
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…
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 and metrics, where only l…
Multivariate Time-series Similarity Assessment via Unsupervised Representation Learning and Stratified Locality Sensitive Hashing: Application to Early Acute Hypotensive Episode Detection
Jwala Dhamala, Emmanuel Azuh, Abdullah Al-Dujaili +2
Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate. Most of the existing approaches are based on the app…
Lipizzaner: A System That Scales Robust Generative Adversarial Network Training
Tom Schmiedlechner, Ignavier Ng Zhi Yong, Abdullah Al-Dujaili +2
GANs are difficult to train due to convergence pathologies such as mode and discriminator collapse. We introduce Lipizzaner, an open source software system that allows machine lear…
AST-Based Deep Learning for Detecting Malicious PowerShell
Gili Rusak, Abdullah Al-Dujaili, Una-May O'Reilly
With the celebrated success of deep learning, some attempts to develop effective methods for detecting malicious PowerShell programs employ neural nets in a traditional natural lan…
Towards Distributed Coevolutionary GANs
Abdullah Al-Dujaili, Tom Schmiedlechner, and Erik Hemberg +1
Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling. Despite their demonstrated success on multiple vision tasks, GANs are d…
On the Application of Danskin's Theorem to Derivative-Free Minimax Optimization
Abdullah Al-Dujaili, Shashank Srikant, Erik Hemberg +1
Motivated by Danskin's theorem, gradient-based methods have been applied with empirical success to solve minimax problems that involve non-convex outer minimization and non-concave…
Revisiting Norm Optimization for Multi-Objective Black-Box Problems: A Finite-Time Analysis
Abdullah Al-Dujaili, S. Suresh
The complexity of Pareto fronts imposes a great challenge on the convergence analysis of multi-objective optimization methods. While most theoretical convergence studies have addre…
On Visual Hallmarks of Robustness to Adversarial Malware
Alex Huang, Abdullah Al-Dujaili, Erik Hemberg +1
A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and wheth…
Approximating Nash Equilibria for Black-Box Games: A Bayesian Optimization Approach
Abdullah Al-Dujaili, Erik Hemberg, Una-May O'Reilly
Game theory has emerged as a powerful framework for modeling a large range of multi-agent scenarios. Many algorithmic solutions require discrete, finite games with payoffs that hav…
Adversarial Deep Learning for Robust Detection of Binary Encoded Malware
Abdullah Al-Dujaili, Alex Huang, Erik Hemberg +1
Malware is constantly adapting in order to avoid detection. Model based malware detectors, such as SVM and neural networks, are vulnerable to so-called adversarial examples which a…
High Throughput 2D Spatial Image Filters on FPGAs
Abdullah Al-Dujaili, Suhaib A. Fahmy
FPGAs are well established in the signal processing domain, where their fine-grained programmable nature allows the inherent parallelism in these applications to be exploited for e…
Multi-Objective Simultaneous Optimistic Optimization
Abdullah Al-Dujaili, S. Suresh
Optimistic methods have been applied with success to single-objective optimization. Here, we attempt to bridge the gap between optimistic methods and multi-objective optimization.…
Embedded Bandits for Large-Scale Black-Box Optimization
Abdullah Al-Dujaili, S. Suresh
Random embedding has been applied with empirical success to large-scale black-box optimization problems with low effective dimensions. This paper proposes the EmbeddedHunter algori…
BMOBench: Black-Box Multi-Objective Optimization Benchmarking Platform
Abdullah Al-Dujaili, S. Suresh
This document briefly describes the Black-Box Multi-Objective Optimization Benchmarking (BMOBench) platform. It presents the test problems, evaluation procedure, and experimental s…