Ai Security

Benchmarking the Security of Open-Weight Models, Part 5: Automated Red-Teaming with NVIDIA Garak
Benchmarking the Security of Open-Weight Models, Part 5: Automated Red-Teaming with NVIDIA Garak

A scanner’s hit rate is a lead, not a measure of risk: most of what garak flagged against Qwen 3.8 was its own detectors mis...

Benchmarking the Security of Open-Weight Models, Part 4: What a Detection Standard Catches, and Why
Benchmarking the Security of Open-Weight Models, Part 4: What a Detection Standard Catches, and Why

Part 3 showed that a harness’s own guardrail can’t see inside file content it reads. This installment layers a product...

Benchmarking the Security of Open-Weight Models, Part 3: The Harness Around the Model
Benchmarking the Security of Open-Weight Models, Part 3: The Harness Around the Model

Parts 1 and 2 benchmarked whether Qwen 3.8 is safe to deploy. This piece asks a different question: once that same model is wired ...

Benchmarking the Security of Open-Weight Models, Part 2: A Local Stack on DGX Spark (with Qwen 3.8 as a Case Study)
Benchmarking the Security of Open-Weight Models, Part 2: A Local Stack on DGX Spark (with Qwen 3.8 as a Case Study)

Part 1 made the case that security benchmarking is a discipline distinct from capability benchmarking. This installment puts it in...

Benchmarking the Security of Open-Weight Models, Part 1: The Problem (with Qwen 3.8 as a Case Study)
Benchmarking the Security of Open-Weight Models, Part 1: The Problem (with Qwen 3.8 as a Case Study)

Capability benchmarks and security benchmarks answer different questions, and most teams only run the first one. Using Alibaba&rsq...

The Harness Is Where Agent Security Lives
The Harness Is Where Agent Security Lives

Three independent 2026 research efforts breached production AI agents without touching the model — and a parallel ‘harness e...