Back to Local Business

Cisco Foundation AI releases Antares models for local security scanning

Cisco's Foundation AI team has released a family of compact, open-weight models designed to identify software vulnerabilities locally.

Opal Keller

August 20, 20262 min read

local AI security - illustration, Jake Team LLC

Cisco’s Foundation AI team has released Antares, a series of compact, open-weight artificial intelligence models intended for agentic vulnerability localization. The model family includes versions with 350 million, 1 billion, and 3 billion parameters. These systems are designed to pinpoint specific files containing security weaknesses within a codebase using only a Common Weakness Enumeration description and read-only repository access.

The 3 billion parameter version is reported to rival larger frontier systems like GPT-5.5 while operating locally at a significantly lower cost. It also outperforms open-source models that are substantially larger. The underlying approach suggests that smaller models trained specifically for security tasks can be more effective than general-purpose giants, allowing source code to remain on local machines.

The 350 million and 1 billion parameter models are publicly available and have accumulated nearly 30,000 downloads on Hugging Face within one month of release.

To facilitate practical use, the team released an Antares Quickstart cookbook. This includes a command-line interface that allows users to profile repositories, check for weaknesses, and generate reports in formats such as SARIF for GitHub Code Scanning. The tool is designed to integrate into continuous integration pipelines with privacy-preserving defaults.

Recent testing on external benchmarks, including a Berkeley cyber-capability suite and a community-built security evaluation, indicated that the models maintain performance outside their training distribution. These results matched the capabilities of hosted agents that incur much higher per-run costs. Additionally, the team introduced two new reasoning benchmarks, CTI-Reasoning and CWE-Prediction, to the FAITH evaluation hub.

These tests measure a model's ability to reason about security using recent data rather than relying on memorized facts.

The Foundation AI team presented Antares and research on automated prompt optimization at Black Hat USA 2026 in Las Vegas. Sessions at the Cisco booth and demonstrations at the AI Kiosk provided opportunities to gather feedback from security researchers and engineers.

The team noted that the event highlighted the potential for open-source prompt optimization to help autonomous agents improve through evaluation results with less manual tuning.

Cisco employs about 2,000 people in Richardson, according to local government records.

Source: Cisco Blogs.

Sources

https://blogs.cisco.com/ai/foundation-ai-in-july-new-models-benchmarks-and-security-research

Share

Opal Keller

Opal Keller reports on local business, new openings, and economic development in Richardson.

Related Stories

Local Business

CAPA adds Caliber and GEICO executives to board

The Certified Automotive Parts Association announced the election of two new board members from the insurance and collision repair sectors.

Opal KellerAugust 26, 20261 min read

More in Richardson

Richardson

City Council Approves Service Center Roof and Maintenance Contract

The city council will consider a cooperative job order contract through the TIPS purchasing system for roof replacement, painting, wall sealing, window glazing, and control joint work at the service center. The approved amount is $415,077.32.

Reese PenningtonAugust 22, 20261 min read