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 7 · SOTA2 Research
Back to Research
Research domain
Adversarial, Safety & Security
Search tasks
Search
10 benchmarks · 2 papers
Watermark Evasion
9 benchmarks · 3 papers
Backdoor Mitigation
9 benchmarks · 2 papers
Image Classification Unlearning
9 benchmarks · 1 papers
Universal Watermark Presence Detection
9 benchmarks · 3 papers
Transferable Adversarial Attack
9 benchmarks · 1 papers
Provenance Tracing
9 benchmarks · 2 papers
Watermark Spoofing
9 benchmarks · 1 papers
Hardware Security Verification
9 benchmarks · 7 papers
Overrefusal evaluation
9 benchmarks · 1 papers
CVSS Base Metric Prediction
9 benchmarks · 1 papers
Lineage Verification
9 benchmarks · 3 papers
Universal Adversarial Attack
9 benchmarks · 2 papers
Poisoned sample detection
9 benchmarks · 8 papers
Safe Text-to-Image Generation
9 benchmarks · 4 papers
Safety Monitoring
9 benchmarks · 3 papers
Environmental Sound Deepfake Detection
9 benchmarks · 4 papers
Prompt Harmfulness Detection
9 benchmarks · 1 papers
Multimodal Safety
9 benchmarks · 1 papers
Node Classification and Link Privacy
9 benchmarks · 2 papers
LLM Red-teaming
9 benchmarks · 2 papers
Morphing Attack Detection
9 benchmarks · 9 papers
Jailbreak Safety Evaluation
9 benchmarks · 3 papers
Poisoning Attack
9 benchmarks · 4 papers
Group Robustness
8 benchmarks · 3 papers
Memorization mitigation
8 benchmarks · 2 papers
Medical Safety Evaluation
8 benchmarks · 1 papers
Multi-bit LLM Watermarking
8 benchmarks · 1 papers
Zero-shot Class Unlearning
8 benchmarks · 5 papers
Privacy Protection
8 benchmarks · 1 papers
Safety-Sensitive Text-to-Image Generation
8 benchmarks · 5 papers
Safe Image Generation
8 benchmarks · 3 papers
Penetration Testing
Page 7 of 103
Previous
Next