Securing CCTV Cameras Against Blind Spots
Jacob Shams
DEF CON 32 Main Stage · Day 1 · Main Stage
In the realm of modern surveillance, Artificial Intelligence (AI)-powered object detectors are increasingly deployed in Closed-Circuit Television (CCTV) systems to automate threat detection and enhance security. However, this talk, "Securing CCTV Cameras Against Blind Spots" by Jacob Shams at DEF CON 32, reveals a critical vulnerability in these systems: their inherent "blind spots" arising from varying detection confidence based on a person's position within the camera frame. Shams' research demonstrates that AI models like **Yolo V3** and **Faster R-CNN** exhibit significant fluctuations in their ability to confidently identify individuals, creating exploitable pathways for evasion.
AI review
This research by Jacob Shams is a critical dissection of AI-powered CCTV systems, revealing inherent, predictable blind spots in object detectors like Yolo V3 and Faster R-CNN. By systematically mapping position-dependent confidence, Shams developed "TipToe," a novel and practical evasion attack that allows individuals to navigate monitored areas with minimal detection, requiring no specialized tools. The work provides indispensable insights for defenders, forcing a fundamental re-evaluation of AI surveillance system reliability and necessitating proactive vulnerability mapping and layered…