Aikido Security Unveils Altar-1 Open-Weight AI for Cybersecurity Defense
Aikido released Altar-1, an open-weight defensive model pruned from GLM-5.3 for on-premises security testing.
Aikido Security released Altar-1, an open-weight model for vulnerability discovery and penetration testing that runs inside customer infrastructure. It is derived from Z.AI's GLM-5.3 and compressed from 1.51 TB to 328 GB with AWQ INT4 quantization and Cerebras REAP pruning that retained 168 of 256 routed experts. On 32 known vulnerabilities across 30 repositories, Altar-1 averaged 60.4 percent recall and rediscovered 23 flaws, compared with 65.6 percent recall and 25 flaws for the full-precision parent. It is on Hugging Face and can run with vLLM on four NVIDIA H200 GPUs, including in the Aikido Machine appliance.
- Altar-1 is an open-weight model for on-premises defensive testing.
- Compression cut the footprint from 1.51 TB to 328 GB.
- It kept 168 of 256 experts and about 92 percent of coverage.
- Internal benchmark recall was 60.4 percent across 32 known flaws.
- Products
- Aikido MachinevLLM
- Organizations
- Hugging Face
From the original article
2 min read at cybersecuritynews.com
Aikido Security has unveiled Altar-1, an open-weight artificial intelligence model designed to run defensive cybersecurity workloads entirely inside an organization’s own infrastructure. The model aims to help security teams use advanced AI for vulnerability discovery and penetration testing without sending source code, internal documentation, or security findings to external cloud-based inference services.
By Abinaya · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.