Publications

2019

Conferences and Workshops

  1. Transfer Learning using Representation Learning in Massive Online Open Courses. John Mucong Ding, Erik Hemberg, Una-May O'Reilly, International Learning Analytics and Knowledge Conference, 2019. arXiv:1812.05043
  2. Using Detailed Access Trajectories for Learning Behavior Analysis. Yanbang Wang, Nancy Law, Erik Hemberg, Una-May O'Reilly,  International Learning Analytics and Knowledge Conference, 2019. arXiv:1812.05767
  3. Adversarially Adapting Deceptive Views and Reconnaissance Scans on a Software Defined Network. Jonathan Kelly, Michael DeLaus, Erik Hemberg, Una-May O'Reilly. 4th IEEE/IFIP International Workshop on Analytics for Network and Service Management (AnNet 2019), 2019.
  4. Improving Genetic Programming with Novel Exploration - Exploitation Control. Jonathan Kelly, Erik Hemberg, Una-May O'Reilly. 22nd European Conference on Genetic Programming (EuroGP), 2019.
  5. On Domain Knowledge and Novelty to Improve Program Synthesis Performance with Grammatical Evolution. Erik Hemberg, Jonathan Kelly, and Una-May O'Reilly. GECCO, 2019.
  6. Spatial Evolutionary Generative Adversarial Networks. Jamal Toutouh, Erik Hemberg and Una-May O'Reilly. GECCO, 2019.
  7. Investigating Algorithms for Finding Nash Equilibria in Cybersecurity Problems. Linda Zhang, Erik Hemberg, SecDef Workshop at GECCO, 2019.
  8. Sign Bits Are All You Need for Black-Box Attacks. Al-Dujaili, A. and O'Reilly, U.-M., in submission
  9. Towards Principled and Efficient Black-Box Min-Max Optimization. Liu, S., Lu, S., Chen, X., Feng, Y., Xu, K., Al-Dujaili, A., Hong, M. and O'Reilly, U.-M., in submission
  10. Categorizing Resources Workshop Papers and Learners for a Finer-Grained Analysis of MOOC Viewing & Doing. Erik Hemberg, Sagar Biswas, Ayesha Bajwa, Nancy Law, Una-May O'Reilly. Learning With MOOCs, 2019.
  11. Analyzing Student Code Trajectories in an Introductory Programming MOOC. Ayesha Bajwa, Erik Hemberg, Ana Bell, Una-May O'Reilly. Learning With MOOCs, 2019.
  12. The Influence of Grades on Learning Behavior in MOOCs: Certification vs. Continued Participation. Li Wang, Erik Hemberg, Una-May O'Reilly. Learning With MOOCs, 2019.
  13. How Student Back- ground and Topic Impact the Doer Effect in Computational Thinking MOOCs. Jitesh Maiyuran, Ayesha Bajwa, Erik Hemberg, Ana Bell, Una-May O'Reilly. Learning With MOOCs, 2019.

Tutorials

  1. Practical Data Science Seminar on practical Data Science. Erik Hemberg. CoLAB Workshop, Uruguay, May 2019.
  2. Spatial Coevolutionary Deep Neural Networks Training. Jamal Toutouh. Universidad de la Republica, Montevideo Uruguay, May 2019.
  3. An Artificial Coevolutionary Framework for Adversarial AI. Jamal Toutouh. Universidad de la Republica, Montevideo Uruguay, May 2019.
  4. Introduction to Genetic Programming. Una-May O'Reilly, Erik Hemberg.GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion. GECCO, 2019.
  5. Introduction to Genetic Programming Tutorial on Genetic Programming. Erik Hemberg. GECCO Tutorial, July 2019
  6. Spatial Coevolutionary Generative Adversarial Networks Hackathon. Erik Hemberg. Oak Ridge National Laboratory, August 2019.
     

Journals

  1. Quantitative EEG reactivity and machine learning for prognostication in hypoxic-ischemic brain injury. Edilberto Amorim, Michellevan der Stoel, Sunil B. Nagaraj, Mohammad M.Ghassemi, JinJing, Una-May O'Reilly,Benjamin M.Scirica, Jong Woo Lee, Sydney S.Cash, M. Brandon Westover. Clinical Neurophysiology. Volume 130, Ussue 10. Oct, 2019. Pg 1908-1916.
     

Abstracts and Posters

  1. On the Use of Context Sensitive Grammars in Genetic Programming For Legal Non-Compliance Detection. Carl Im, Erik Hemberg. GECCO, 2019
  2. On the Influence of Grades on Learning Behavior of Students in MOOCs. Li Wang, Erik Hemberg and Una-May O'Reilly, Learning At Scale, 2019. (Work-In-Progress)
  3. Investigating Learning Design Categorization and Learning Behaviour in Computational MOOCS. Sagar Biswas, Erik Hemberg, Nancy Law and Una-May Oreilly, Learning At Scale, 2019. (Work-In-Progress)
  4. Student Code Trajectories in an Introductory Programming MOOC. Ayesha Bajwa, Ana Bell, Erik Hemberg and Una-May O'Reilly, Learning At Scale, 2019. (Work-In-Progress)
  5. Representation Learning for Code Malware. Sanja Simonovikj, Abdullah Al-Dujaili, Shashank Srikant, Erik Hemberg, Una-May O'Reilly. IBM AI Research Week, AI Horizons Colloquium, 2019.
     

Theses

  1. Analyzing Student Learning Trajectories in an Introductory Programming MOOC. Ayesha Bajwa, M.Eng., MIT-EECS, June 2019. Advisors: Erik Hemberg, Una-May O'Reilly.
  2. Investigating Genetic Prigramming with Novelty and Domain Knowledge for Program Synthesis. Jonathan Kelly, M.Eng., MIT-EECS, June 2019. Advisors: Erik Hemberg, Una-May O'Reilly.
  3. Investigating Coevolutionary Algorithms for Finding Nash Equilibria in Cybersecurity Problems. Linda Zhang, M.Eng., MIT-EECS, June 2019. Advisors: Erik Hemberg, Una-May O'Reilly.
  4. The Influence of Grades on Learning Behavior of Students in MOOCs. Li Wang, M.Eng., MIT-EECS, June 2019. Advisors: Erik Hemberg, Una-May O'Reilly.
  5. Structured Grammatical Evolution Applied to Program Synthesis. Andrew Zhang, M.Eng., MIT-EECS, June 2019. Advisors: Erik Hemberg, Una-May O'Reilly.
  6. Master of Engineering Thesis. Carolyn Holz, M.Eng., MIT-EECS, June 2019. Advisors: Erik Hemberg, Una-May O'Reilly.

 

2018

Conferences and Workshops

  1. Lipizzaner: A System That Scales Robust Generative Adversarial Network Training. Erik Hemberg, Abdullah Al-Dujaili, Tom Schmiedlechner, Una-May O'Reilly, Systems for Machine Learning workshop@ NeurIPS 2018. arxiv: 1811.12843
  2. An Artificial Coevolutionary Framework for Adversarial AI. Una-May O’Reilly, Erik Hemberg. AAAI Fall Symposia, Washington DC, 2018.
  3. Towards Distributed Coevolutionary GANs. Abdullah Al-Dujaili, Tom Schmiedlechner, Erik Hemberg, Una-May O'Reilly. AAAI Fall Symposia, Washington DC, 2018.
  4. Adversarial Co-evolution of Attack and Defense in a Segmented Computer Network Environment. Erik Hemberg, Joe Zipkin, Richard Skowyra, Neal Wagner and Una-May O’Reilly. GECCO SECDEF Workshop, 2018.
  5. EuroGP 2018 Panel Debate: Genetic Programming in the Era of Deep Neural Networks. Machado, Penousal and O'Reilly, Una-May and Gori, Marco and Risi, Sebastian. SIGEVOlution, July 2018. Vol: 11, No 2. Aug 2018. Iss: 1931-8499, Pg 3-6. ACM, New York, NY, USA, 2018.
  6. Adversarial Deep Learning for Robust Detection of Binary Encoded Malware. Abdullah Al-Dujaili, Alex Huang, Erik Hemberg, and Una-May O'Reilly. Deep Learning and Security Workshop, IEEE Security and Privacy, 2018. arXiv:1801.02950
  7. Approximating Nash Equilibria for Black-Box Games: A Bayesian Optimization Approach. Abdullah Al-Dujaili, Erik Hemberg, and Una-May O'Reilly. International Workshop on Optimization in Multiagent Systems, @FAIM18. (AAMAS, ICML, IJCAI/ECAI, ICCBR, SoCS), 2018. arxiv: 1804.10586
  8. On Visual Hallmarks of Robustness to Adversarial Malware. Alex Huang, Abdullah Al-Dujaili, Erik Hemberg, and Una-May O'Reilly. IReDLiA@FAIM18 (AAMAS, ICML, IJCAI/ECAI, ICCBR, SoCS), 2018. arxiv: 1805.03553
  9. On the Application of Danskin's Theorem to Derivative-free Minimax Optimization. Abdullah Al-Dujaili, Shashank Srikant, Erik Hemberg, and Una-May O'Reilly. Int. Workshop on Global Optimization, 2018. arxiv: 1805.06322
  10. AST-Based Deep Learning for Detecting Malicious PowerShell.  Gili Rusak, Abdullah Al-Dujaili, Una-May O’Reilly. In Proceedings of 2018 ACM SIGSAC Conference on Computer & Communications Security (CCS ’18). ACM, New York, NY, USA, 3 pages. arxiv: 1810.09230
  11. Exploring the Use of Autoencoders for Botnets Traffic Representation. Ruggiero Dargenio, Shashank Srikant, Erik Hemberg, Una-May O'Reilly. IEEE Symposium on Security and Privacy Workshops 2018: 57-62.
  12. 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, Jonathan Rubin, Una-May O'Reilly. Machine Learning for Health (ML4H) Workshop at NeurIPS, 2018. arXiv:1811.07216
  13. An Artificial Coevolutionary Framework for Adversarial AI. Una-May O'Reilly, Erik Hemberg. Proceedings of the AAAI Symposium on Adversary-Aware Learning Techniques and Trends in Cybersecurity (ALEC 2018), Association for the Advancement of Artificial Intelligence 2018 Fall Symposium Series (AAAI-FSS 2018) Arlington, Virginia, USA, October 18-20, 2018. Vol 2269 pp 50-55. 2018.

Abstracts and Posters

  1. Machine Learning Tools for Analyzing the Development of Neuronal Networks in Health and Disease. Raoul-Emil R. Khouri, Susanna B. Mierau, Przemyslaw Jarzebowski, Ole Paulsen, Erik Hemberg , Una-May O'Reilly. 2nd North East Computational Health Summit AI in Healthcare, 27 April 2018.
  2. Competitive Coevolutionary Algorithm Decision Support. Daniel Sanchez, Marcos Pertierra, Erik Hemberg and Una-May O’Reilly. Poster, GECCO, 2018.
  3. Machine Learning and Malware Arms Race. Abdullah Al-Dujaili, Alex Huang, Erik Hemberg, Una-May O'Reilly. IBM Research 2018 Horizons Colloquium. Cambridge MA. Oct, 2018 (Best poster Award)
  4. AST-Based Deep Learning for Detecting Malicious PowerShell.  Gili Rusak, Abdullah Al-Dujaili, Una-May O’Reilly. In Proceedings of 2018 ACM SIGSAC Conference on Computer & Communications Security (CCS ’18), ACM, New York, NY, USA.
     

Theses

  1. Investigating EEG Burst Suppression for Coma Outcome Prediction.Tiange Zhan, M.Eng., MIT EECS, June 2018. Advisors: Erik Hemberg, Una-May O'Reilly.
  2. Investigating Coevolutionary Algorithms for Expensive Fitness Evaluations In Cybersecurity. Marcos Pertierra Arrojo, M.Eng., MIT EECS, June 2018. Advisors: Erik Hemberg, Una-May O'Reilly.
  3. Two-Photon Calcium Imaging Sequence Analysis Pipeline: A Method for Analyzing Neuronal Network Activity. Raoul-Emil Roger Khouri, M.Eng., MIT EECS, June 2018. Advisors: Erik Hemberg, Una-May O'Reilly.
  4. Understanding the Doer Effect for Computational Subjects with MOOCs. Jitesh Maiyuran, M.Eng., MIT EECS, June 2018. Advisors: Erik Hemberg, Una-May O'Reilly.
  5. Visualizing Adversaries - Transparent Pooling Approaches for decision Support in Cybersecurity. Daniel Prado Sanchez, M.Eng., MIT EECS, June 2018. Advisors: Erik Hemberg, Una-May O'Reilly
     

Journals and Book Chapters

  1. Grammatical Evolution with Coevolutionary Algorithms in Cyber Security. Erik Hemberg, Anthony Erb Lugo, Dennis Garcia, Una-May O’Reilly. pp 407-431, Handbook of Grammatical Evolution, Springer 2018.

 

2017

Conferences and Workshops

  1. Distributed Stratified. Locality Sensitive Hashing for Critical Event Prediction in the Cloud. De Palma, Alessandro and Hemberg, Erik and O'Reilly, Una-May. NIPS ML4H, 2017.
  2. Towards Formalizing Statute Law as Default Logic through Automatic Semantic Parsing. Pertierra, Marcos and Lawsky, Sarah and Hemberg, Erik and O’Reilly, Una-May. ISAIL, 2017.
  3. Towards evolutionary machine learning comparison, competition, and collaboration with a multi-cloud platform. Pasquale Salza, Erik Hemberg, Filomena  Ferrucci, Una-May O'Reilly. GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017.
  4. Investigating coevolutionary archive based genetic algorithms on cyber defense networks. Dennis Garcia, Anthony Erb Lugo, Erik Hemberg, Una-May O'Reilly. GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017.
  5.  Machine Learning or Discrete Choice Models for Car Ownership Demand Estimation and Prediction. Miguel Paredes, Erik Hemberg, Una-May O'Reilly, and Chris Zegras. Conference Proceedings of the 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2017. Naples, Italy. (in presss)
  6.  If You Can't Measure It, You Can't Improve It: Moving Target Defense Metrics. Stjepan Picek, Erik Hemberg, Una-May O'Reilly. Proceedings of the 2017 Workshop on Moving Target Defense, 2017. 
  7. CryptoBench: benchmarking evolutionary algorithms with cryptographic problems. Stjepan Picek, Domagoj Jakobovic, Una-May O'Reilly. GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017.
  8. Developing proactive defenses for computer networks with coevolutionary genetic algorithms. Anthony Erb Lugo, Dennis Garcia, Erik Hemberg, Una-May O'Reilly. SecDEF GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017.
  9. cCube: a cloud microservices architecture for evolutionary machine learning classification. Pasquale Salza, Erik Hemberg, Filomena Ferrucci, Una-May O'Reilly. GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2017.
  10. Collision frequency locality-sensitive hashing for prediction of critical events. Y. Bryce Kim, Erik Hemberg, Una-My O'Reilly.  EMBC2017: 3088-3093.
  11. Distributed Stratified Locality Sensitive Hashing for Critical Event Prediction in the Cloud. Alessandro De Palma, Erik Hemberg, Una-May O'Reilly. CoRRabs/1712.00206 (2017).
  12. One-Class Classification of Low Volumes DoS Attacks with Genetic Programming. Stjepan Picek and Erik Hemberg and Una-May O'Reilly. Genetic Programming Theory & Practice. 2017. (in press)
     

Abstracts and Posters

  1. Maintaining and Extending MOOC Clickstream Curation in the MOOC-Learner-Project. Austin Liew, Erik Hemberg, Una-May O’Reilly Learning with MOOCs Conference, 2017. Austin, TX.
  2. Exploring Stopout Prediction and Transfer Learning in MOOCs. Alex Huang, Erik Hemberg, Una-May O’Reilly. Learning with MOOCs Conference, 2017. Austin, TX.
     

Theses

  1. Cohort Selection and Sampling Techniques to Balance Time-Series Retrospective Studies. Brian Bell Jr, M.Eng., MIT EECS, February 2017. Advisor: Una-May O'Reilly.
  2. Extensions to Behavioral Genetic Programming. Steven B. Fine, M.Eng., MIT EECS, February 2017. Advisor: Una-May O'Reilly.
  3. Coevolutionary Genetic Algorithms for Proactive Computer Network Defenses. Anthony Erb Lugo, M.Eng., MIT EECS, June 2017. Advisor: Una-May O'Reilly.
  4. BeatDB v3: A Framework for the Creation of Predictive Datasets from Physiological Signals. Steven Rivera, M.Eng., MIT EECS, June 2017. Advisor: Una-May O'Reilly.
  5. Overcoming Code Rot in Legacy Software Projects. Austin Liew, M.Eng., MIT EECS, June 2017. Advisor: Una-May O'Reilly.
  6. Long Short-term Memory Recurrent Neural Networks for Classification of Acute Hypotensive Episodes. Alexander Jaffe, M.Eng., MIT EECS, June 2017. Advisor: Una-May O'Reilly.
  7. Peer-to-Peer Network Modeling for Adversarial Proactive Cyber Defenses. Dennis Garcia, M.Eng., MIT EECS, June 2017. Advisor: Una-May O'Reilly.
  8. Physiological Time Series Retrieval and Prediction with Locality-Sensitive Hashing. Y. Bryce Kim, PhD, MIT EECS, June 2017. Advisor: Una-May O'Reilly.
     

Journals and Book Chapters

  1. Exploiting Subprograms in Genetic Programming. Fine, Steven and Hemberg, Erik and Krawiec, Krzysztof and O'Reilly, Una-May. Genetic Programming Theory and Practice XV (Genetic and Evolutionary Computation), 2017.
     

Edited Volumes

  1. Proceedings of the 9th International Joint Conference on Computational Intelligence. Christophe Sabourin, Juan Julián Merelo Guervós, Una-May O'Reilly, Kurosh Madani, Kevin Warwick. IJCCI 2017, Funchal, Madeira, Portugal, November 1-3, 2017. SciTePress2017, ISBN 978-989-758-274-5.

     

2016

Conferences

  1. Analysis of Locality-Sensitive Hashing for Fast Critical Event Prediction on Physiological Time Series. Y. Bryce Kim and Una-May O'Reilly. 38th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016: 783-787.  NSF Award for Young Professionals Contributing to Smart and Connected Health.
  2. Stratified locality-sensitive hashing for accelerated physiological time series retrieval. Y. Bryce Kim, Erik Hemberg, Una-May O'Reilly. EMBC2016: 24792483.
  3. STEALTH: Modeling Coevolutionary Dynamics of Tax Evasion and Auditing. Una-May O'Reilly. KDIR2016: 9.
  4. STEALTH: Modeling Coevolutionary Dynamics of Tax Evasion and Auditing. Una-May O'Reilly. IJCCI (ECTA)2016: 11.
  5. Multi-Line Batch Scheduling by Similarity. Ignacio Arnaldo, Erik Hemberg, Una-May O'Reilly. GECCO '16 Companion Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion, 2016.
  6. Dynamics of Adversarial Co-evolution in Tax Non-Compliance Detection. Jacob Rosen, Erik Hemberg, Una-May O'Reilly. GECCO '16 Companion Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion, 2016.
     

Tutorials

  1. Genetic Programming: A Tutorial Introduction. Una-May O'Reilly. GECCO '16 Companion Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion, 2016.
     

Abstracts and Posters

  1. Multi-Resolution Histogram Representation for Physiological Time Series and its Integration into Locality-Sensitive Hashing. Y. Bryce Kim and Una-May O'Reilly. Poster in 38th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016.
     

Workshops

  1. Dynamics of Adversarial Co-evolution in Tax Non-Compliance Detection. Jacob Rosen, Erik Hemberg, Una-May O’Reilly. GECCO Security & Risk Workshop, 2016. DOI:http://dx.doi.org/10.1145/2908961.2931680
  2. Multi-Line Batch Scheduling by Similarity. Ignacio Arnaldo, Erik Hemberg, Una-May O’Reilly. GECCO Industrial Applications of Metaheuristics Workshop, 2016. DOI:http://dx.doi.org/10.1145/2908961.2931647
  3. Stratified Locality-Sensitive Hashing for Sublinear Time Critical Event Prediction. Y. Bryce Kim, Erik Hemberg, and Una-May O'Reilly. Conference on Neural Information Processing Systems (NIPS) Machine Learning in Healthcare Workshop, 2016. NSF Best Paper Award.
     

Theses

  1. Towards An Automatic Predictive Question Formulations. Benjamin J. Schreck, M.E. thesis, MIT Dept of EECS, June 2016. Advisor: Kalyan Veeramachaneni.
  2. Model Factory: A New Way to Look at Data Through Models. Yonglin Wu, M.E. thesis, MIT Dept of EECS, June 2016. Advisor: Kalyan Veeramachaneni.
  3. Transfer Learning for Predictive Models in MOOCs. Sebastien Boyer, M.S. thesis, MIT Dept of EECS, IDSS, June 2016. Advisor: Kalyan Veeramachaneni.
  4. The Synthetic Data Vault: Generative Modeling for Relational Databases. Neha Patki, M.E. thesis, MIT Dept of EECS, June 2016. Advisor: Kalyan Veeramachaneni.
  5. Artificial Intelligence Opportunities and an End-To-End Data-Driven Solution for Predicting Hardware Failures. Mario Orozco Gabriel, M.S., MBA thesis, MIT Dept of Mechanical Engineering, Sloan School of Management, June 2016. Advisors: Kalyan Veeramachaneni, Tauhid Zaman, John J. Leonard.
     

Journals and Book Chapters

  1. Detecting Tax Evasion: A Co-Evolutionary Approach. Erik Hemberg, Jacob Rosen, Geoff Warner, Sanith Wijesinghe, Una-May O'Reilly. Artificial Intelligence and Law, 1-34, 2016. DOI 10.1007/s10506-016-9181-6.
  2. Investigating Multi-Population Competitive Coevolution for Anticipating Tax Evasion. Erik Hemberg, Jacob Rosen, Una-May O'Reilly. Genetic Programming: Theory to Practice, 2016.

     

Name note: Articles by Dr. O'Reilly

Dr. O'Reilly consistently publishes under the name Una-May O'Reilly with the abbreviation U.M. O'Reilly. However there are numerous citations of her papers which are inconsistent in citing her name. Popular errors (try to spot them!) are Una May O'Reilly, Una-May O Reilly, OReilly, Una M, U-M or U.-M. or U-M. with many combinations of the preceding errors which mangle the hyphen or apostrophe. We have even found that different fonts have different apostrophes so that two equivalent citations are not attributed to the same paper!

A few sources have incomplete but somewhat extensive lists of my publications:

Older Publications...