Categories
Companies
Research
Sign in
Join
Loading the SOTA2 catalog…
WizWand is now SOTA2 Research
SOTA2
Research
Papers
Benchmarks
Datasets
Tasks
Adversarial, Safety & Security AI research · SOTA2 Research
Back to Research
Research domain
Adversarial, Safety & Security
Search tasks
Search
518 benchmarks · 144 papers
Machine Unlearning
422 benchmarks · 214 papers
Safety Evaluation
398 benchmarks · 123 papers
Membership Inference Attack
347 benchmarks · 123 papers
Deepfake Detection
339 benchmarks · 182 papers
Jailbreak Attack
330 benchmarks · 137 papers
Adversarial Attack
227 benchmarks · 111 papers
Generative Modeling
182 benchmarks · 59 papers
Watermark Detection
150 benchmarks · 57 papers
Backdoor Defense
139 benchmarks · 60 papers
Vulnerability Detection
117 benchmarks · 55 papers
Jailbreak Defense
115 benchmarks · 22 papers
Safe Reinforcement Learning
110 benchmarks · 34 papers
Backdoor Detection
107 benchmarks · 65 papers
Jailbreaking
94 benchmarks · 45 papers
Safety Classification
94 benchmarks · 25 papers
Jailbreak Detection
89 benchmarks · 70 papers
Adversarial Robustness
89 benchmarks · 42 papers
Backdoor Attack
86 benchmarks · 25 papers
Membership Inference
74 benchmarks · 30 papers
Targeted Adversarial Attack
66 benchmarks · 24 papers
Attack Detection
61 benchmarks · 32 papers
Preference Alignment
60 benchmarks · 41 papers
Safety Alignment
59 benchmarks · 30 papers
Unlearning
58 benchmarks · 25 papers
Prompt Injection Defense
56 benchmarks · 13 papers
AIGI Detection
56 benchmarks · 20 papers
Adversarial Detection
55 benchmarks · 20 papers
Prompt injection detection
53 benchmarks · 6 papers
Fuzzing
53 benchmarks · 23 papers
Robustness Evaluation
51 benchmarks · 42 papers
Bias Evaluation
46 benchmarks · 15 papers
Adversarial Attack Detection
Page 1 of 103
Previous
Next