💻 Technology 1d ago

Researcher poisons open-weight AI model for under $100

The Register
Biting commentary and tech news from the UK
View Channel →
Researcher poisons open-weight AI model for under $100
Source ↗ 👁 0 💬 0
The AI supply chain is, in some ways, even more vulnerable to poisoning than that of traditional software. Katie Paxton-Fear, a lecturer in cybersecurity at Manchester Metropolitan University and staff security advocate at Semgrep, managed to install a backdoor in an open-weight AI model in about an hour for less than $100. "I started out by trying to figure out if I could use fine tuning to get a model to swap from camelCase for JavaScript to snake_case, and it was actually really easy, even if

Comments (0)

Sign in to join the discussion

More Like This

Nvidia launches Cosmos 3 Edge model and expands its physical AI push in Japan
SiliconANGLE · 1d ago
Verizon shedding stores signals a shift in the way the carrier does business
Android Police · 1d ago
Why Apple Sued OpenAI, New York Takes on Data Centers, and What to Know about Cyclosporiasis
WIRED · 1d ago
TSMC boosts Arizona fab investment by $100B after strong second quarter
SiliconANGLE · 1d ago
China Just Dropped Another Bomb on America’s Frontier AI Companies
Gizmodo · 1d ago
My favorite Obsidian alternative isn't Logseq or Joplin, it's a block-based app that's actually more private
XDA · 1d ago