Selected publications
- I Arnaldo, K Veeramachaneni. The Holy Grail of “Systems for Machine Learning”: Teaming humans and machine learning for detecting cyber threats. ACM SIGKDD Explorations Newsletter 21 (2), 39-47, 2019.
- A Arun, I Arnaldo. Shooting the moving target: machine learning in cybersecurity. USENIX Conference on Operational Machine Learning (OpML 19), 13-14, 2019.
- I Arnaldo, K Veeramachaneni, M Lam. eX2: a framework for interactive anomaly detection. Intelligent User Interfaces workshops, 2019.
- I Arnaldo, A Arun, S Kyathanahalli, K Veeramachaneni. Acquire, adapt, and anticipate: continuous learning to block malicious domains. IEEE International Conference on Big Data (Big Data), 1891-1898, 2018.
- Ignacio Arnaldo, Alfredo Cuesta-Infante, Ankit Arun, Mei Lam, Costas Bassias, Kalyan Veeramachaneni. Learning representations for log data in cybersecurity. International Conference on Cyber Security Cryptography and Machine Learning, 2017.
- Kalyan Veeramachaneni, Ignacio Arnaldo, Vamsi Korrapati, Constantinos Bassias, and Ke Li. AI2: Training a big data machine to defend. In 2016 IEEE 2nd International Conference on Big Data Security on Cloud, 2016.
- Ignacio Arnaldo, Kalyan Veeramachaneni, Andrew Song, and Una-May O’Reilly. Bring Your Own Learner: A cloud-based, data-parallel commons for machine learning. In IEEE Computational Intelligence Magazine, 2015.
- Ignacio Arnaldo, Una-May O’Reilly, and Kalyan Veeramachaneni. Building Predictive Models via Feature Synthesis. In Proceedings of the 2015 on Genetic and Evolutionary Computation Conference, 2015.
In general press
- CBS news: Artificial intelligence could help predict cyber attacks
- MIT news: System predicts 85 percent of cyber-attacks using input from human experts
- CSO Online: AI + humans = kick-ass cybersecurity
- CIO today: MIT Develops Machine Learning AI To Detect Cyberattacks
- Dark reading: MIT AI Researchers Make Breakthrough On Threat Detection.
- Tech republic: MIT shows how AI cybersecurity excels by keeping humans in the loop
Patents
- Method and system for learning representations for log data in cybersecurity. Patent date: Issued Jul 30, 2019. Patent issuer and number: US10367841
- Copula optimization method and apparatus for identifying and detecting threats to an enterprise or e-commerce system and other applications. Patent date: Issued Aug 7, 2018. Patent issuer and number: US10044762
- Method and system for training a big data machine to defend. Patent date: Issued Feb 27, 2018. Patent issuer and number: US9904893
- Method and apparatus for identifying and detecting threats to an enterprise or e-commerce system. Patent date: Issued Dec 29, 2016. Patent issuer and number: US9661025
- Computer-implemented process and system employing outlier score detection for identifying and detecting scenario-specific data elements from a dynamic data source. Patent date: Issued Apr 16, 2019. Patent issuer and number: US10264027