RollingEvidence: Autoregressive Video Evidence via Rolling Shutter Effect
Feng Qian
34th USENIX Security Symposium (USENIX Security '25) · Day 1 · System Security 1: Threat Detection, Exploitation, and Adaptive Defenses
In an era increasingly defined by sophisticated AI-driven manipulations, the integrity of video evidence has become a critical concern. The "RollingEvidence" system, presented by Feng Qian from Ant Group at USENIX Security, offers a novel and robust solution to this burgeoning problem. This talk introduces a system designed to create and verify authentic videos by leveraging a unique property of camera sensors: the **rolling shutter effect**. By embedding invisible, tamper-resistant probes directly into video frames during recording, RollingEvidence aims to restore transparency and trustworthiness to visual documentation, which is vital for legal, security, and justice applications.
AI review
Genuinely clever repurposing of a hardware artifact — the rolling shutter effect — as a cryptographically anchored authentication primitive. The core idea is elegant: something camera engineers have treated as a bug for 20 years becomes an unforgeable evidence channel. Solid engineering, honest evaluation metrics, and a real threat model make this stand out from the usual deepfake-detection noise.