AI & Enterprise
Cisco unveils \'Antares\' open-weight small models focused on detecting code vulnerabilities
Cisco has unveiled Antares, a family of small language models designed to flag files in code repositories that are likely to contain known security vulnerabilities. It distributed Antares-350M and Antares-1B as open-weight models on Hugging Face and plans to release a larger Antares-3B. Developed by Cisco Foundation AI, Antares links public vulnerability data, security advisories and common weakness classifications to repository files.
