NewsThe Register — Security
Researcher poisons open-weight AI model for under $100
Teaser from the source
Models demand trust without offering verification
This is the RSS-feed teaser. Read the full article at the original source.
Read at The Register — SecurityMore on open-weight
Other news entries
- Microsoft, Nvidia push provenance checks as open-weight AI adoption acceleratesNewsCSO Online
- Rolling the cyber dice with open-source and open-weight AI modelsNewsCSO Online
- Advertisers are trying to influence AI bots with secret adsNewsThe Register — Security
- Cisco’s new AI model tells code reviewers where to look for vulnerabilitiesNewsCSO Online
- Cisco's open-weight bug busters take on Google and OpenAINewsThe Register — Security
- Cisco Launches Low-Cost AI Models for Source Code SecurityNewsSecurityWeek
- Frontier LLMs couldn't help Hugging Face fight off evil agentsNewsThe Register — Security
- Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight ModelsNewsThe Hacker News
ID