jumplander/JL-ActionBoundary-1K-v0.1.0
Viewer • Updated • 1k • 1
Edit Datasets filters
Active filters: agent-safety
OzLabs/gatling-adversarial-563k
Viewer • Updated • 542k • 51
osunlp/AutoElicit-Seed
Viewer • Updated • 361 • 42 • 1
osunlp/AutoElicit-Bench
Viewer • Updated • 117 • 61 • 1
tianyyuu/clawdbot_safety_testing
Viewer • Updated • 34 • 24
cogniarch/benchmarks
Preview • Updated • 42
xunyoyo/clawkeeper
Viewer • Updated • 6 • 113
shaw/scambench-training
Updated • 62
benchflow/ClawsBench
Viewer • Updated • 7.83k • 251 • 3
aditya593/SafetyDrift-traces
Viewer • Updated • 5 • 57 • 2
TrustAIRLab/HarmfulSkillBench
Viewer • Updated • 200 • 117 • 4
CaiZhiTech/Evaluation-Dataset-of-AI-Agent-Security-Guardrails
Viewer • Updated • 1.02k • 34
lihaonan0716/mcphunt-agent-traces
Updated • 45 • 1
UCSC-VLAA/CIK-Bench
Viewer • Updated • 202 • 288
mcphunt-benchmark/mcphunt-agent-traces
Preview • Updated • 78 • 1
aradhye/agent-safety-bench
Viewer • Updated • 4.22k • 51 • 1
sightact-bench/sightact-bench-14family
Updated • 22
goldenash/MAD-Bench
Viewer • Updated • 360 • 24
anonSubmission678/anon_submission_neurips
Viewer • Updated • 263 • 7
anonymous-skillchainbench/skillchainbench
Updated • 4
anonymous-skillchainbench/skillchainbench-code
Updated • 61
sairights/safeclawbench
Updated • 322
mindbomber/aana-harmactions-agent-action-gate
Updated • 10
mindbomber/aana-gap-posthoc-gate
Updated • 9
mindbomber/aana-gap-domain-adapter-ablation
Updated • 21
mindbomber/aana-cross-domain-action-gate-validation
Updated • 3
mindbomber/aana-cross-domain-action-gate-blind-v2
Updated • 9
mindbomber/aana-cross-domain-action-gate-v2-tuned
Updated • 10
mindbomber/aana-cross-domain-action-gate-v2-all-domains-tuned
Updated • 9
mindbomber/aana-cross-domain-action-gate-blind-v3
Updated • 14