Published in Computers & Security, 2025
A method to identify unlabeled security patches in open-source software by combining code diffs, commit messages, and developer activity metadata.
Recommended citation: Nitzan Farhi, Noam Koenigstein, Yuval Shavitt, "PatchView: Multi-modality detection of security patches." Computers & Security, Vol. 151, 104356, 2025.
Download Paper
Published in arXiv / AAAI AICS, 2023
Identifies security patches across repositories using developer activity and commit metadata, without relying on source code analysis.
Recommended citation: Nitzan Farhi, Noam Koenigstein, Yuval Shavitt, "Detecting Security Patches via Behavioral Data in Code Repositories." arXiv preprint arXiv:2302.02112 / AAAI Workshop on Artificial Intelligence for Cyber Security (AICS), 2023.
Download Paper
Published in Environmental Science: Water Research & Technology, 2022
Uses an LSTM neural network to forecast the Sludge Volume Index (SVI) using operational sensor measurements from a wastewater treatment plant.
Recommended citation: Efrat Kohen, Nitzan Farhi, Yuval Shavitt, Hadas Mamane, "Prediction of a full scale WWTP activated sludge SVI test using an LSTM neural network." Environmental Science: Water Research & Technology, Vol. 8, No. 11, pp. 2786-2795, 2022.
Download Paper
Published in OpenReview / ICLR, 2022
Evaluates exponential temporal aggregation for long time-series sequences in LSTM networks to preserve recent detail while summarizing past context.
Recommended citation: Nitzan Farhi, Yuval Shavitt, "A Study of Aggregation of Long Time-series Input for LSTM Neural Networks." OpenReview, 2022.
Download Paper
Published in Environmental Technology & Innovation, 2021
Uses LSTM recurrent neural networks to predict effluent quality parameters from sensor data at a municipal wastewater treatment plant.
Recommended citation: Nitzan Farhi, Efrat Kohen, Hadas Mamane, Yuval Shavitt, "Prediction of wastewater treatment quality using LSTM neural network." Environmental Technology & Innovation, Vol. 23, 101632, 2021.
Download Paper
Published in Computers & Security, 2019
A study on keystroke impersonation attacks using custom USB hardware and a defense framework based on acoustic and timing side-channel data.
Recommended citation: Nitzan Farhi, Nir Nissim, Yuval Elovici, "Malboard: A novel user keystroke impersonation attack and trusted detection framework based on side-channel analysis." Computers & Security, Vol. 85, pp. 240-269, 2019.
Download Paper