All posts
-
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 Review: Lakera, NeMo, Bedrock, and Beyond
A practitioner's comparison of the leading AI guardrail tools in 2026 — Lakera Guard, NVIDIA NeMo, AWS Bedrock Guardrails, and Guardrails AI — covering
-
Best LLM Red Teaming Tools 2026: A Practitioner's Evaluation
A hands-on comparison of the leading LLM red teaming tools in 2026 — PyRIT, Garak, Promptfoo, and manual frameworks — with capability matrices
-
How to Test AI Agent Security: A Practical Evaluation Guide
Testing AI agent security requires a different approach than static LLM red-teaming. This guide covers the attack surface, test methodology, and the OWASP
-
Designing a Reproducible AI-Security Eval Harness
A reproducible AI-security evaluation is an engineering artifact, not a notebook. Here's the harness design — separation of corpus, target, judge, and
-
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.
-
Comparing LLM Safety Benchmarks: AdvBench, HarmBench, JailbreakBench
AdvBench, HarmBench, and JailbreakBench are not interchangeable, and treating them as one undermines every comparison built on top.
-
Red-Team Eval Methodology: Pairing 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 Done Right
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 produce wildly different production outcomes. Here's where benchmark fidelity actually breaks down and what to measure