As the researchers report, LeftoverLocals does not concern ordinary consumers, but developers of machine learning (ML) and large language models (LLM) models. The vulnerability exploits features of the GPU architecture and isolates memory by pumping out data. An attacker can “hack” the GPU via the programmable interface and dump data on the GPU.

LeftoverLocals provides high data download speeds, which poses a serious threat to the security of cloud computing platforms. For example, using an AI model with 7 billion parameters in a single call to the AMD Radeon RX 7900 XT graphics card, the data leak rate was 5.5 MB.

The researchers said they shared the vulnerability monitoring report and details with the mentioned GPU manufacturers.

Source: Ferra

Previous articleStartup Recraft, founded by a former Yandex employee, raised $12 million
Next articleGoogle will carry out another wave of staff cuts to invest in AI
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.

LEAVE A REPLY

Please enter your comment!
Please enter your name here