Detecting Deepfakes: From Classical Physics to Deep Learning

About the talk

As the world braces for the largest election year with over 64 nations heading to the polls, the influence of artificial intelligence looms large, poised to make a profound impact. From the proliferation of misinformation to the emergence of deepfakes and the exploration of positive use cases, the landscape of political discourse is undergoing a seismic shift.

In this session, Gautham Koorma and Romit Barua will discuss the following:

1. A classical physics based forensic technique for detecting manipulation in images
2. The approaches from their paper on detecting cloned voices and issues related to generalization of ML models for deepfake detection on “in the wild” media
3. A modern deep learning based technique for detecting fake videos

Have questions for the speakers? Leave a comment.

About the speakers

Gautham Koorma is a Machine Learning Engineer and Researcher working on deep learning models for audio signal processing and computer vision. He has recently graduated with a Master’s in Information Science from UC Berkeley, specializing in machine learning, digital forensics, policy, product management, and entrepreneurship.

Romit Barua is a Machine Learning Researcher and has previously worked as Head of Investment Control at Texas Exchange Bank and Risk Analyst at Q Investments. He has also recently graduated with a Master’s in Management Information Systems from UC Berkeley, specializing in Data Science. His research at UC Berkeley focused on audio deepfake detection.

Rumanu will be moderating the talk. She is a Machine Learning Researcher who has spent her weekends for the past five years at tech meetups and conferences, her interest peaking at the intersection of adtech and data privacy preservation. She toys around with humor(ous?) NLP usecases when not hitting comedy open mics to be a better tech speaker.

RSVP and venue

This session will be held online on the 28nd of March from 8 pm - 9 pm. You can RSVP to participate via Zoom or watch the livestream on YouTube.

About the Deepfakes series

This session is part of a series on Deepfake technologies which will explore socio-political, technical, and governance aspects of the technology.

About Anthill Inside

Anthill Inside is a community where topics in AI and Deep Learning such as tools and technologies, methodologies and strategies for incorporating AI and Deep Learning into various applications and businesses, and AI engineering are discussed. Furthermore, Anthill Inside places a strong emphasis on exploring and addressing ethical concerns, privacy, and the issue of bias both in practice and within AI products.

How you can contribute to Anthill Inside

1. Post a talk proposal to suggest a topic you’d like to discuss. This should involve a brief outline of the use cases and challenges regarding AI implementation.
2. Moderate/discuss a topic someone else is proposing.
3. Spread the word among colleagues and friends.
4. Join The Fifth Elephant Telegram group or WhatsApp group.

Contact Information

Follow us on Twitter at @anthillin. For queries, write to editorial@hasgeek.com or call +91-7676332020.