AI Security
In-depth guides and analysis on ai security from the Safeguard engineering team.
676 articles
Refusal Rate Analysis: Griffin AI vs Mythos
A security AI that refuses too often is useless. One that refuses too rarely is dangerous. Griffin AI publishes calibrated refusal benchmarks; Mythos does not.
Does GitHub Copilot Use Your Code? IP and Licensing Questions Answered
Does GitHub Copilot steal your code, or just learn patterns from it? The honest answer depends on which setting you're using, what plan you're on, and whether the suggestion it hands back matches code it was trained on.
Enterprise LLM Budget Management Patterns
LLM spend forecasting is where finance teams meet AI engineering for the first time. The patterns that produce predictability are specific.
Griffin AI vs DeepSeek Coder for Security Review
DeepSeek Coder has become a favourite for code-focused workloads. This is how it compares to Griffin AI when the job is security review, not code generation.
Exploit Path Synthesis: Griffin AI vs Mythos
Finding a bug is not the same as proving it is exploitable. How Griffin AI synthesises concrete exploit paths and why pure-LLM scanners rarely get past the sketch stage.
Throughput At Scale: Griffin AI vs Mythos
Engine work parallelises cleanly. Model calls do not. We explain why Griffin AI's throughput scales with CPU while Mythos-class tools bottleneck on rate limits.
RAG Pipeline Supply Chain Attacks: Vector DBs and More
RAG pipelines have six or seven supply chain surfaces, and most teams are only watching one. Here is how the attacks actually look in production.
SEvenLLM Design And Coverage
SEvenLLM set out to measure how well LLMs handle Security Event analysis, the unglamorous day-to-day work of SOCs and IR teams. A design review of what the benchmark covers, how it was built, and where the coverage maps or does not map to real operations.
Griffin AI vs Claude Haiku for Bulk Scanning
Claude Haiku is the cost-efficient model Griffin uses for high-volume scan interpretation. Here's how raw Haiku compares to Haiku inside Griffin's bulk pipeline.
Audit Log Completeness: Griffin AI vs Mythos
Audit logs are where enterprise AI either proves its seriousness or exposes its improvisation. The gap between Griffin AI and Mythos-class products is visible in the first day of a real audit.
Griffin AI vs OpenAI o1 for Security Reasoning
Deep reasoning models are transformative for hard logical problems. Security reasoning is only partially a logic problem—the rest is grounding, policy, and workflow.
Small-Model Distillation For Security Workflows
Distillation compresses the capability of a large model into a small one for a narrow task. For high-volume security workflows, it is often the difference between a working pipeline and an unaffordable one.