Advancements in facial recognition
summary
Companies race to detect live deepfakes after a reported Hong Kong breach where several executives were simultaneously spoofed to authorize multi‑million transfers, and a keynote demos real‑time forgeries. Vendors tout iProov approved certification from the Photo Alliance, server‑side checks that spot copy‑of‑copy spectral artifacts in images, and active liveness methods like patterned light liveness that project randomized colors onto faces to prove presence. The focus is on measurable signals, deployed detectors, and how many attacks each method actually stops.
AI-written summary · about
related talks
28mFace spoofing detection: theory and practice
39mBeyond Recognition: A Cautionary Tale of AI and Identity Fraud
30mReality Under Attack: Just How Serious Is the Deep Fake Threat?
27mIs now the time to solve the deepfake threat?
28mDefending our reality in the era of deepfakes
46mTackling Deepfakes, Wars, and Other Security Threats in the GenAI World
26mVirtual U: Defeating Face Liveness Detection by Building Virtual Models...
27mAl-Generated Attacks: The New Era of Threats to Authentication