Please ensure Javascript is enabled for purposes of website accessibility

AI Research Blog

Spotting Deepfakes in Online Meetings: A Practical Guide for Non-Experts

We provide practical observations that can help non-technical users become more aware of potential synthetic media during online interactions.

Niv Amitay, AI Cyber “Red Team” Lead
February 1, 2025

Building Resilient Models: Lessons from Video Augmentation in Deepfake Detection

We share our experiences implementing various augmentation techniques and how they've helped our models generalize beyond controlled environments.

Eli Passov, AI Detection Lead
January 1, 2025

Building Resilient Models: Audio Augmentation in Deepfake Detection

We discuss techniques we've explored for creating audio variations that help models recognize synthetic voices across different acoustic environments.

Talia Ben Simon, AI Voice Researcher
January 1, 2025

Reliability-Weighted Ensembles: Advancing Deepfake Defense

We explain our ensemble approach that combines specialized detectors with a novel reliability-weighting mechanism.

Eli Passov, AI Detection Lead
January 1, 2025

From Lab to Production: The Critical Role of Rigorous AI Evaluation

We share how our evaluation framework evolved to better predict production performance through comprehensive testing methodologies.

Ilia Kravets, VP Engineering
December 1, 2024

Explainable AI in Action: Lessons from Building Our Deepfake Analysis Studio

We discuss our journey building an explainable detection system that provides transparency into why specific media is flagged as synthetic.

Allon Oded, VP Product
November 1, 2024

Deepfake Techniques Explained: Why Some Work in Real-Time and Others Don't

We explore the taxonomy of synthetic media methods, from face swaps to voice cloning, examining why some are suitable for video conferencing while others require offline processing.

Niv Amitay, AI Cyber “Red Team” Lead
November 1, 2024

AI threats are evolving.
Your protection should too.