All articles
-
AI Firewall Placement: Lakera, NeMo, Bedrock, Azure
Where Lakera Guard, NeMo Guardrails, Bedrock Guardrails, and Azure AI Content Safety sit in the LLM request path, and what each placement costs.
-
AI Security Benchmarks: A Reference to 10 Test Suites
What AdvBench, HarmBench, JailbreakBench, AgentDojo, AgentHarm, Agent-SafetyBench, SEC-bench, CyberSecEval, PINT, and RAID each measure, and where each stops.
-
AI Security Testing: A Method for LLM and Agent Systems
AI security testing across four layers: how to scope an assessment, which published standards supply the test cases, which tools run them, and what to report.
-
How to Benchmark LLM Security: A Repeatable Method
Benchmark LLM security repeatably: define the threat model, pick suites that map to it, pin the target, and report attack success rate with refusal rate.
-
Open Source LLM Security Scanners: A Practitioner's Field Guide
Garak, NeMo Guardrails, PyRIT, and ARTKIT compared: how the leading open source LLM security scanners differ on coverage, fit, and maintenance.
-
How AI Model Evaluation Metrics Work: A Practitioner's Guide
How AI model evaluation metrics work, from BLEU and ROUGE to BERTScore, perplexity, MMLU, and LLM-as-a-Judge: when each applies and where it fails.
-
The AI Security Tools Directory: 40+ Tools Compared (2026)
A maintained 2026 directory of 40+ AI and LLM security tools, comparing scanners, runtime guardrails, injection detection, and observability.
-
Best AI Guardrail Tools 2026: Lakera vs NeMo vs Bedrock
A comparison of the leading AI guardrail tools in 2026, covering Lakera Guard, NVIDIA NeMo, AWS Bedrock Guardrails, and Guardrails AI on real trade-offs.
-
Best LLM Red Teaming Tools 2026: A Practitioner's Evaluation
A documentation-based comparison of the leading LLM red teaming tools in 2026: PyRIT, Garak, Promptfoo, and the HarmBench and JailbreakBench test sets.
-
How to Test AI Agent Security: A Practical Evaluation Guide
Testing AI agent security needs a different approach than static LLM red teaming. The attack surface, a test methodology, and the OWASP agentic checklist.
-
Designing a Reproducible AI-Security Eval Harness
A reproducible AI-security evaluation is an engineering artifact, not a notebook. The harness design that separates corpus, target, judge, and report.
-
Measuring Prompt-Injection Robustness in Tool-Using Agents
Prompt-injection robustness for an agent is not a single number — it is utility-under-attack against targeted attack success.
-
AdvBench vs HarmBench vs JailbreakBench: Key Differences
AdvBench, HarmBench, and JailbreakBench are not interchangeable, and treating them as one undermines every comparison built on top.
-
Red-Team Eval Methodology: Attack Success Rate With Refusal Rate
An LLM red-team evaluation that reports attack success rate without reporting refusal rate is half a measurement.
-
Benchmarking LLM Jailbreak Resistance: Attack Success Rate
Attack success rate is the headline metric for jailbreak resistance, and almost everyone computes it in a way that isn't comparable across runs.
-
Reproducible LLM Scanner Benchmarks: What Everyone Forgets to Pin
An LLM security scanner benchmark that isn't pinned to a model version, a seed, and a corpus hash isn't reproducible.
-
Benchmarking Jailbreak Classifiers: The Asymmetry Nobody Reports
Jailbreak classifiers are graded on attack recall and almost never on the cost of being wrong. That asymmetry is the whole story. Here's how to measure it.
-
How to Benchmark a Prompt-Injection Detector Honestly
Most prompt-injection detector benchmarks are broken before the first request. Here is a test design that produces a number you can actually trust.
-
LLM Benchmark Fidelity: Why MMLU Won't Predict Production Quality
Models with identical MMLU scores behave very differently in production. Where benchmark fidelity breaks down and what to measure instead before shipping.