Fusion

FUSION - the 1st RHML Implementation

Our team focuses on the development of interactive AI systems that embody the principles of human-in-the-loop and reciprocal human–machine learning (RHML). We believe that meaningful human-AI collaboration can reduce model bias, prevent degradation, and support mutual learning. To operationalize this vision, we design and implement systems that facilitate continual, two-way feedback between human experts and ML models. One such system is Fusion, an RHML-based platform that allows domain experts to iteratively improve classifiers, understand model decisions, and integrate human knowledge. Fusion has been successfully applied in cybersecurity and is adaptable to a wide range of NLP tasks.  An open source version of Fusion will soon be available on GitHub - contact us for more information.

Related publications include:

  1. Cohen, D., Te’eni, D., Schwartz, D.G., Yahav, I., Silverman, G., Mann, Y. & Lewinsky, D., Human –AI Enhancement of Cyber Threat Intelligence, International Journal of Information Security, 2025, https://doi.org/10.1007/s10207-025-01004-4.

  2. Lewinsky, D., Te’eni. D., Yahav, I., Schwartz, D.G., Silverman, G. & Mann, Y., Detecting terrorist influencers using reciprocal human-machine learning: The case of militant Jihadist Da'wa on the Darknet, Humanities and Social Sciences Communications, 11, 1442. 2024. https://doi.org/10.1057/s41599-024-03920-7.

  3. Te’eni, D, Zagalsky, A, Yahav, I, Schwartz, DG, Silverman, G, Cohen, D, Mann,Y & Lewinsky, D, Reciprocal Human-Machine Learning: A Theory and an Instantiation for the Case of Message Classification. Management Science, 2023 https://doi.org/10.1287/mnsc.2022.03518.