no code implementations • ICML 2020 • Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah Al-Dujaili, Mingyi Hong, Una-May O'Reilly
In this paper, we study the problem of constrained min-max optimization in a black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values.
no code implementations • 13 Jan 2024 • Erik Hemberg, Stephen Moskal, Una-May O'Reilly
Algorithms that use Large Language Models (LLMs) to evolve code arrived on the Genetic Programming (GP) scene very recently.
no code implementations • 10 Oct 2023 • Stephen Moskal, Sam Laney, Erik Hemberg, Una-May O'Reilly
We present prompt engineering approaches for a plan-act-report loop for one action of a threat campaign and and a prompt chaining design that directs the sequential decision process of a multi-action campaign.
1 code implementation • 21 Nov 2022 • Jinghan Jia, Shashank Srikant, Tamara Mitrovska, Chuang Gan, Shiyu Chang, Sijia Liu, Una-May O'Reilly
We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models.
no code implementations • 29 Sep 2021 • Shashank Srikant, Benjamin Lipkin, Anna A Ivanova, Evelina Fedorenko, Una-May O'Reilly
We find that the Multiple Demand system, a system of brain regions previously shown to respond to code, contains information about multiple specific code properties, as well as machine learned representations of code.
no code implementations • 25 Aug 2021 • Chathika Gunaratne, Rene Reyes, Erik Hemberg, Una-May O'Reilly
Contagious respiratory diseases, such as COVID-19, depend on sufficiently prolonged exposures for the successful transmission of the underlying pathogen.
no code implementations • 5 Aug 2021 • Erik Hemberg, Una-May O'Reilly
Artificial Intelligence (AI) and Machine Learning (ML) algorithms can support the span of indicator-level, e. g. anomaly detection, to behavioral level cyber security modeling and inference.
no code implementations • 25 Jun 2021 • Jamal Toutouh, Erik Hemberg, Una-May O'Reilly
Generative adversary networks (GANs) suffer from training pathologies such as instability and mode collapse, which mainly arise from a lack of diversity in their adversarial interactions.
no code implementations • 23 Apr 2021 • Prakruthi Karuna, Erik Hemberg, Una-May O'Reilly, Nick Rutar
Scaling the cyber hunt problem poses several key technical challenges.
1 code implementation • ICLR 2021 • Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shiyu Chang, Quanfu Fan, Gaoyuan Zhang, Una-May O'Reilly
We further show that our formulation is better at training models that are robust to adversarial attacks.
no code implementations • 10 Feb 2021 • Jamal Toutouh, Una-May O'Reilly
Generative adversarial networks (GANs) exhibit training pathologies that can lead to convergence-related degenerative behaviors, whereas spatially-distributed, coevolutionary algorithms (CEAs) for GAN training, e. g. Lipizzaner, are empirically robust to them.
1 code implementation • 1 Oct 2020 • Erik Hemberg, Jonathan Kelly, Michal Shlapentokh-Rothman, Bryn Reinstadler, Katherine Xu, Nick Rutar, Una-May O'Reilly
Many public sources of cyber threat and vulnerability information exist to serve the defense of cyber systems.
Cryptography and Security
no code implementations • 28 Sep 2020 • Jacob M. Springer, Bryn Marie Reinstadler, Una-May O'Reilly
Neural networks are well-known to be vulnerable to imperceptible perturbations in the input, called adversarial examples, that result in misclassification.
no code implementations • 3 Aug 2020 • Jamal Toutouh, Erik Hemberg, Una-May O'Reilly
We investigate the impact on the performance of two algorithm components that influence the diversity during coevolution: the performance-based selection/replacement inside each sub-population and the communication through migration of solutions (networks) among overlapping neighborhoods.
1 code implementation • ICLR 2020 • Abdullah Al-Dujaili, Una-May O'Reilly
Similar performance is observed on a standard IMAGENET model with an average of $579$ queries.
no code implementations • 8 Apr 2020 • Shashank Srikant, Nicolas Lesimple, Una-May O'Reilly
We investigate the problem of classifying a line of program as containing a vulnerability or not using machine learning.
no code implementations • 7 Apr 2020 • Jamal Toutouh, Una-May O'Reilly, Erik Hemberg
We investigate training Generative Adversarial Networks, GANs, with less data.
no code implementations • 7 Apr 2020 • Emiliano Perez, Sergio Nesmachnow, Jamal Toutouh, Erik Hemberg, Una-May O'Reilly
Generative adversarial networks (GANs) are widely used to learn generative models.
no code implementations • 7 Apr 2020 • Una-May O'Reilly, Jamal Toutouh, Marcos Pertierra, Daniel Prado Sanchez, Dennis Garcia, Anthony Erb Luogo, Jonathan Kelly, Erik Hemberg
We delineate Adversarial Genetic Programming for Cyber Security, a research topic that, by means of genetic programming (GP), replicates and studies the behavior of cyber adversaries and the dynamics of their engagements.
1 code implementation • 30 Mar 2020 • Jamal Toutouh, Erik Hemberg, Una-May O'Reilly
In machine learning, ensembles of predictors demonstrate better results than a single predictor for many tasks.
1 code implementation • 30 Sep 2019 • Sijia Liu, Songtao Lu, Xiangyi Chen, Yao Feng, Kaidi Xu, Abdullah Al-Dujaili, Minyi Hong, Una-May O'Reilly
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 function but may query its values.
1 code implementation • 29 May 2019 • Jamal Toutouh, Erik Hemberg, Una-May O'Reilly
We contribute a superior evolutionary GANs training method, Mustangs, that eliminates the single loss function used across Lipizzaner's grid.
no code implementations • 19 Feb 2019 • 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 $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available.
no code implementations • 14 Dec 2018 • Yanbang Wang, Nancy Law, Erik Hemberg, Una-May O'Reilly
Student learning activity in MOOCs can be viewed from multiple perspectives.
no code implementations • 12 Dec 2018 • Mucong Ding, Yanbang Wang, Erik Hemberg, Una-May O'Reilly
It consists of two alternative transfer methods based on representation learning with auto-encoders: a passive approach using transductive principal component analysis and an active approach that uses a correlation alignment loss term.
1 code implementation • 30 Nov 2018 • Tom Schmiedlechner, Ignavier Ng Zhi Yong, Abdullah Al-Dujaili, Erik Hemberg, Una-May O'Reilly
GANs are difficult to train due to convergence pathologies such as mode and discriminator collapse.
no code implementations • 14 Nov 2018 • Jwala Dhamala, Emmanuel Azuh, Abdullah Al-Dujaili, Jonathan Rubin, Una-May O'Reilly
Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate.
no code implementations • 3 Oct 2018 • 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 language processing setup while others employ convolutional neural nets to detect obfuscated malicious commands at a character level.
no code implementations • 21 Jul 2018 • Abdullah Al-Dujaili, Tom Schmiedlechner, and Erik Hemberg, Una-May O'Reilly
Generative Adversarial Networks (GANs) have become one of the dominant methods for deep generative modeling.
1 code implementation • 9 May 2018 • Alex Huang, Abdullah Al-Dujaili, Erik Hemberg, Una-May O'Reilly
A central challenge of adversarial learning is to interpret the resulting hardened model.
1 code implementation • 27 Apr 2018 • 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.
Computer Science and Game Theory
2 code implementations • 9 Jan 2018 • Abdullah Al-Dujaili, Alex Huang, Erik Hemberg, Una-May O'Reilly
We are inspired by them to develop similar methods for the discrete, e. g. binary, domain which characterizes the features of malware.
no code implementations • 1 Dec 2017 • Alessandro De Palma, Erik Hemberg, Una-May O'Reilly
The availability of massive healthcare data repositories calls for efficient tools for data-driven medicine.
no code implementations • 14 Aug 2014 • Colin Taylor, Kalyan Veeramachaneni, Una-May O'Reilly
Even with more difficult prediction problems, such as predicting stop out at the end of the course with only one weeks' data, the models attained AUCs of 0. 7.