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 9 · SOTA2 Research
Back to Research
Research domain
Adversarial, Safety & Security
Search tasks
Search
7 benchmarks · 3 papers
Jailbreak Resistance
7 benchmarks · 1 papers
Synthetic fingerprint detection
7 benchmarks · 3 papers
Class-level Unlearning
7 benchmarks · 1 papers
Watermark similarity restoration
7 benchmarks · 2 papers
Behavioral Steering
7 benchmarks · 1 papers
Sample-level unlearning
7 benchmarks · 2 papers
Class-level Machine Unlearning
7 benchmarks · 1 papers
Long-term state poisoning evaluation
7 benchmarks · 1 papers
Fuzzing (Unique crash-inducing sequences discovery)
7 benchmarks · 1 papers
Agent Safety Judgment
7 benchmarks · 3 papers
Memory Poisoning Attack
7 benchmarks · 1 papers
Upstream Backdoor Detection
7 benchmarks · 3 papers
Fake News Classification
7 benchmarks · 6 papers
Harmfulness Detection
7 benchmarks · 1 papers
Speaker Impersonation Attack
7 benchmarks · 3 papers
Embedding Inversion
7 benchmarks · 3 papers
Adversarial Transfer Attack
7 benchmarks · 4 papers
Perturbation Detection
7 benchmarks · 2 papers
Unknown attack detection
7 benchmarks · 1 papers
Poisoning Defense Evaluation
7 benchmarks · 5 papers
Model Steering
7 benchmarks · 2 papers
Safety Refusal Evaluation
7 benchmarks · 2 papers
Side-channel leakage analysis
7 benchmarks · 2 papers
Safe Exploration
7 benchmarks · 3 papers
Safety Guardrailing
7 benchmarks · 1 papers
Untargeted identity retrieval attack
7 benchmarks · 5 papers
Adversarial Purification
7 benchmarks · 6 papers
Model Inversion
7 benchmarks · 6 papers
Response Harmfulness Detection
7 benchmarks · 1 papers
Out-of-Taxonomy Risk Detection
7 benchmarks · 4 papers
Privacy Attribute Recognition
7 benchmarks · 2 papers
Modeling Attack
Page 9 of 103
Previous
Next