Chinese Students Develop AI-Evading 'Invisibility Cloak'

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.

Graduate students at Wuhan University, supervised by Professor Wang Zheng, have developed the InvisDefense coat, which uses AI-designed patterns and thermal elements to evade detection by AI-powered surveillance cameras. While no harm has occurred, the technology poses future risks of security breaches and misuse by enabling individuals to bypass AI surveillance systems.[AI generated]

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

The event involves an AI system indirectly, as the cloak is designed to defeat AI-based surveillance systems that use machine vision and infrared imaging for pedestrian detection. The development and use of this cloak could plausibly lead to harms such as violations of security, public safety risks, or interference with critical infrastructure monitoring. No direct harm has been reported yet, so it does not qualify as an AI Incident. The article focuses on the invention and its capabilities, not on responses or updates to prior incidents, so it is not Complementary Information. Hence, the event is best classified as an AI Hazard due to the credible risk of future harm from the cloak's use to evade AI surveillance.[AI generated]
AI principles
Robustness & digital securitySafetyAccountabilityTransparency & explainabilityRespect of human rights

Industries
Government, security, and defenceDigital security

Affected stakeholders
GovernmentGeneral public

Harm types
Public interest

Business function:
Research and development

AI system task:
Recognition/object detectionContent generation


Articles about this incident or hazard