Research domain
Adversarial, Safety & Security
Machine Unlearning518 benchmarks · 144 papersSafety Evaluation422 benchmarks · 214 papersMembership Inference Attack398 benchmarks · 123 papersDeepfake Detection347 benchmarks · 123 papersJailbreak Attack339 benchmarks · 182 papersAdversarial Attack330 benchmarks · 137 papersGenerative Modeling227 benchmarks · 111 papersWatermark Detection182 benchmarks · 59 papersBackdoor Defense150 benchmarks · 57 papersVulnerability Detection139 benchmarks · 60 papersJailbreak Defense117 benchmarks · 55 papersSafe Reinforcement Learning115 benchmarks · 22 papersBackdoor Detection110 benchmarks · 34 papersJailbreaking107 benchmarks · 65 papersSafety Classification94 benchmarks · 45 papersJailbreak Detection94 benchmarks · 25 papersAdversarial Robustness89 benchmarks · 70 papersBackdoor Attack89 benchmarks · 42 papersMembership Inference86 benchmarks · 25 papersTargeted Adversarial Attack74 benchmarks · 30 papersAttack Detection66 benchmarks · 24 papersPreference Alignment61 benchmarks · 32 papersSafety Alignment60 benchmarks · 41 papersUnlearning59 benchmarks · 30 papersPrompt Injection Defense58 benchmarks · 25 papersAIGI Detection56 benchmarks · 13 papersAdversarial Detection56 benchmarks · 20 papersPrompt injection detection55 benchmarks · 20 papersFuzzing53 benchmarks · 6 papersRobustness Evaluation53 benchmarks · 23 papersBias Evaluation51 benchmarks · 42 papersAdversarial Attack Detection46 benchmarks · 15 papers