Standardized benchmark for AI safety scanners. Run your scanner, get a score. From Authensor / 15 Research Lab.
-
Updated
Mar 15, 2026 - TypeScript
#
authensor
Here are 7 public repositories matching this topic...
Can AI systems detect when they're being evaluated? Research paper and reference implementation exploring the Hawthorne Effect for AI.
benchmarking evaluation red-team ai-safety deceptive-alignment authensor 15-research-lab hawthorne-effect
-
Updated
Mar 15, 2026 - TypeScript
AI security payloads and wordlists. Prompt injection, jailbreaks, model exploitation. The SecLists of AI. From the team behind 350+ verified vulnerabilities across the ML ecosystem.
security jailbreak owasp pentesting seclists payloads red-team ai-safety security-testing wordlists red-teaming ai-security adversarial-ml prompt-injection llm-security authensor 15-research-lab
-
Updated
May 14, 2026 - HTML
Behavioral fingerprinting for AI agents. Build profiles, detect drift, identify compromise.
-
Updated
Mar 15, 2026 - TypeScript
Map the attack surface of AI agents. Enumerates tools, capabilities, and security gaps. SARIF output. From the team behind 126 responsible disclosures across NVIDIA, Microsoft, Meta, Google.
-
Updated
Mar 16, 2026 - TypeScript
Black box recorder for AI agents. Reconstruct decisions, detect anomalies, verify audit chains. Part of the Authensor safety stack.
-
Updated
Mar 15, 2026 - TypeScript
Bidirectional mapping between MITRE ATT&CK and AI alignment failure modes. The rosetta stone between cybersecurity and AI safety.
-
Updated
Mar 15, 2026 - HTML
Improve this page
Add a description, image, and links to the authensor topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the authensor topic, visit your repo's landing page and select "manage topics."