Researchers Demonstrate Makeup Can Bypass Facial Recognition AI

Thumbnail Image

The information displayed in the AIM should not be reported as representing the official views of the OECD or of its member countries.

Researchers at Ben-Gurion University of the Negev showed that both digitally and physically applied makeup patterns can fool advanced facial recognition systems with up to 98% success. This exposes a significant vulnerability in AI-based security systems, potentially enabling individuals to evade identification in real-world scenarios.[AI generated]

Why's our monitor labelling this an incident or hazard?

The event involves the use and testing of AI systems (facial recognition) and AI-assisted tools (digital makeup patterns) to bypass these systems. While the study shows a clear vulnerability and potential for misuse that could lead to harm (e.g., evading surveillance or identification), the article only reports experimental results without any realized harm or incident. Therefore, this qualifies as an AI Hazard, as the development and use of makeup patterns to fool facial recognition systems could plausibly lead to harms such as privacy violations or misuse in real-world scenarios.[AI generated]
AI principles
Robustness & digital securitySafetyAccountability

Industries
Government, security, and defenceDigital security

Affected stakeholders
GovernmentGeneral public

Harm types
Public interest

Business function:
Compliance and justice

AI system task:
Recognition/object detection


Articles about this incident or hazard