Category

Cybersecurity: RL environments and AI benchmarks

RL environments
1
AI benchmarks
40
Shares entries with
7 categories

Snapshot 2026-10-11. How categories are built · Where the data comes from

The galaxy could not load. See every vendor on the board.

Cybersecurity across the universe: its 1 confirmed entry is lit. Hover a star for its name; click to open it.

In short

What are RL environments for cybersecurity?
A simulated workplace where an AI agent practises a task (a code repository, a browser, business software) and an automatic grader scores each attempt. Labs train on thousands of these attempts. Bought to improve models.
Who builds RL environments for cybersecurity?
Rise Data Labs.

RL environments 1

  1. Rise Data Labs

AI benchmarks 40

None confirmed yet.

40 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. Gray Swan IPI — Combined Attack Set
  2. ExploitBench v8-bench
  3. RedSage-Bench
  4. SecCodeBench
  5. HardSecBench
  6. MIRROR
  7. CyberChainBench
  8. CyBiasBench
  9. ExploitGym
  10. HIDBench
  11. Honeyquest for LLMs
  12. Honeyval
  13. PinTrace
  14. VulnLLM-R
  15. When the Manual Lies
  16. CWE-Bench
  17. AIRTBench
  18. CVE-Bench
  19. OrgForge-IT
  20. CIPHER
  21. From Prompt Injection to Persistent Control
  22. GraphIP-Bench
  23. Membership Inference on LLMs in the Wild
  24. SastBench: A Benchmark for Testing Agentic SAST Triage
  25. Send a SCOUT First
  26. WebTrap Park
  27. Decoupled Web Penetration Testing Benchmark
  28. Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports
  29. Multi-Source Cybersecurity Logs
  30. NYU LLM CTF
  31. OASB Skills Security Benchmark
  32. SEC-bench
  33. DFIR-Metric
  34. BountyBench
  35. Cybersecurity CTFs
  36. Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python
  37. ADR: An Agentic Detection System for Enterprise Agentic AI Security
  38. CrackMeBench
  39. Hidden State Poisoning Attacks against Mamba-based Language Models
  40. Multi-View Decompilation Benchmark

Domains that overlap with Cybersecurity

Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.