Aggregator

Deep learning systems on phones, cars, and other edge devices increasingly run on custom silicon. Specialized chips such as FPGAs and ASICs give these systems the speed and low power consumption that edge applications need. Many of these chips come from third-party design houses and foundries, which adds steps to the supply chain where an outside party can alter a device. Researchers at the University of Tennessee and the University of Florida built an attack … More →

The post A hardware neural network backdoor that hides in plain sight appeared first on Help Net Security.

Light switches. How on earth is it so hard to find decent light switches?! It sounds ridiculous until you actually spend enough time looking for ones that meet two simple criteria:

1. Aren't stateful (switch is up or down, has to be push-button)
2. Looks good

Now, I'

Defense contractors build AI systems that task drones automatically and propose kill-chains to support soldiers. Several of these contractors have partnered with frontier AI companies to put advanced models into military tools. Anduril works with OpenAI, Palantir works with Microsoft, and Lockheed Martin works with Meta. The systems coming out of these partnerships carry a security problem that sits outside the methods of arms control diplomacy: confirming what an AI model will do. Verification built … More →

The post Proving what a military AI model will do is the real problem appeared first on Help Net Security.