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 – Page 2 · SOTA2 Research
Back to Research
Research domain
Adversarial, Safety & Security
Search tasks
Search
45 benchmarks · 7 papers
Video Deepfake Detection
42 benchmarks · 26 papers
LLM Alignment
42 benchmarks · 10 papers
Learning to Defer
38 benchmarks · 18 papers
Red Teaming
37 benchmarks · 26 papers
Jailbreak
37 benchmarks · 12 papers
Safety Detection
36 benchmarks · 9 papers
Website Fingerprinting
36 benchmarks · 24 papers
Jailbreak Robustness
33 benchmarks · 30 papers
Human Evaluation
33 benchmarks · 8 papers
Model Fingerprinting
33 benchmarks · 8 papers
Safety Moderation
32 benchmarks · 5 papers
LLM Jailbreaking
30 benchmarks · 4 papers
Reliability Assessment
29 benchmarks · 22 papers
Safety
29 benchmarks · 9 papers
Model Inversion Attack
29 benchmarks · 20 papers
Knowledge Unlearning
28 benchmarks · 14 papers
Targeted Attack
28 benchmarks · 17 papers
Jailbreak Attack Evaluation
28 benchmarks · 15 papers
Untargeted Adversarial Attack
28 benchmarks · 10 papers
Harmful Content Detection
27 benchmarks · 11 papers
Safety Alignment Evaluation
26 benchmarks · 14 papers
Sycophancy Evaluation
26 benchmarks · 13 papers
Indirect Prompt Injection Defense
25 benchmarks · 15 papers
LLM Unlearning
25 benchmarks · 11 papers
Harmfulness Evaluation
24 benchmarks · 11 papers
Prompt Injection Attack
23 benchmarks · 1 papers
Cultural safety evaluation
23 benchmarks · 7 papers
Prompt Classification
23 benchmarks · 7 papers
Malicious Prompt Detection
23 benchmarks · 5 papers
Deepfake Attribution
23 benchmarks · 15 papers
Attack Success Rate
23 benchmarks · 6 papers
Attack Success Rate Evaluation
Page 2 of 103
Previous
Next