Explore talks and videos
Filter by research area, year and venue. Every filter is in the address bar, so you can share a view as a link.
Deepfakes & multimodalFact-checking & verification
Presenting: The Bellingcat Online Open Source Investigations ToolkitBellingcat presents their newly restructured Online Open Source Investigations Toolkit, an AI-powered search interface that aggregates tools for digital verification and investigative research. The toolkit provides categorized access to resources for satellite imagery, social media analysis, transportation tracking, and source archiving,…
Deepfakes & multimodalPlatforms, policy & society
Digital Forensic Expert Breaks Down Political DeepfakesFarid surveys the state of deepfake technology in the 2024 election cycle, demonstrating how synthetic images, audio, and video are weaponized to manipulate voters through fake endorsements, false statements, and inauthentic imagery. He details forensic detection techniques—perspective geometry, shadow physics, lip-sync analysis—that…
Deepfakes & multimodalPlatforms, policy & society
How deepfakes undermine truth and threaten democracyDeepfakes use machine-learning technology to create fabricated audio and video of people doing or saying things they never did. Law professor Danielle Citron explores the dual threats: individual harm (non-consensual sexual deepfakes targeting women, especially minorities and journalists) and societal damage (eroding trust in…
Spread & networksDeepfakes & multimodal
Don't Blame Bots, Fake News Is Spread by HumansA comprehensive talk covering the scale of misinformation campaigns on social media (ranging from Syrian hackers compromising the AP's Twitter account to Russian interference in the 2016 US election), empirical findings on how false news spreads faster than truth, and emerging threats from synthetic media (deepfakes) created via…
Deepfakes & multimodalDetection methods
The Erosion of Shared Reality in the Age of DeepfakesGenerative AI has moved from nascent to commodity in just 18 months; text-to-image, text-to-video, and real-time interactive deepfakes are now trivial to create. Humans are bad at detecting them (performing ~60% accuracy on trained tasks vs. 50% chance).