AI Security
In-depth guides and analysis on ai security from the Safeguard engineering team.
676 articles
Griffin AI vs Gemini Ultra for Security Reasoning
Gemini Ultra sets a high bar on complex reasoning benchmarks. But security reasoning is not benchmark reasoning. Here's how Griffin AI's engine-first approach changes the outcome.
CycloneDX Support: Griffin AI vs Mythos
CycloneDX is not a text format to be summarized — it's a typed graph with dozens of semantically-rich fields. Griffin AI consumes it as a graph. Mythos-class tools consume it as tokens. That difference decides every downstream finding.
Training Data Provenance: The Regulatory Wave
Regulators across three continents are converging on a single demand: show where your training data came from. The engineering implications are larger than most labs have admitted.
Call Graph Depth Compared: Griffin AI vs Mythos
Shallow call graphs miss real exploits; deep graphs surface them. We examine how Griffin AI and Mythos-class tools differ on depth, and why it matters.
Enforcing container compliance with Azure Policy
How Azure Policy enforces container compliance on AKS—registry restriction, regulatory mapping, and where admission-time policy alone falls short.
Eval Methodology: Griffin AI vs Mythos
A benchmark number is only as good as the methodology that produced it. Here is how Griffin AI builds its harness and why most Mythos-class tools cannot be audited.
SQL Injection Chains: Griffin AI vs Mythos
SQL injection stopped being a single-line bug years ago. Modern chains stitch a tainted parameter through ORMs, caches, background jobs, and downstream services. Griffin AI's engine-plus-LLM architecture follows the taint across those hops; Mythos-class pure-LLM scanners summarise one file at a time and lose the thread.
Hypothesis Quality: Griffin AI vs Mythos
Two AI bug hunters can both generate hypotheses. Only one can defend them. A field study of grounded versus ungrounded hypothesis generation in zero-day discovery.
Vulnerability Scanning for AI Models: A New Frontier
AI models ship with dependencies, use vulnerable libraries, and introduce novel attack surfaces. Traditional scanning is not enough.
Securing Claude Code MCP Server Deployments
Claude Code MCP servers run with the privileges of the developer who invoked them. That makes deployment posture the entire security model.
Air-Gapped Environments: Griffin AI vs Mythos
Air-gapped AI is not a feature flag. It is an architectural commitment, and it separates serious enterprise products from consumer-grade assistants.
Per-Scan Token Cost: Griffin AI vs Mythos
Tiered models and a deterministic engine cut token consumption to the moments that need reasoning. Pure-LLM tools pay full price for every trivial check.