Alibaba-AAIG

Alibaba-AAIG's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

Yuanxh 

updated 2 models 7 days ago

Alibaba-AAIG/YuFeng-XGuard-Reason-8B

Text Generation • 8B • Updated 7 days ago • 100

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

0.8B • Updated 7 days ago • 172 • 2

nora19980 

updated 2 models 13 days ago

Alibaba-AAIG/YuFeng-XGuard-Reason-8B

Text Generation • 8B • Updated 7 days ago • 100

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

0.8B • Updated 7 days ago • 172 • 2

Yuanxh 

updated a collection 16 days ago

YuFeng-XGuard-Reason

Collection

YuFeng-XGuard-Reason is a series of guardrail models specifically designed for content safety. It is engineered to accurately identify security risks • 2 items • Updated 12 days ago

phecy 

updated a model 19 days ago

Alibaba-AAIG/YuFeng-XGuard-Reason-8B

Text Generation • 8B • Updated 7 days ago • 100

qwe123dsacxz 

updated 2 models 19 days ago

Alibaba-AAIG/YuFeng-XGuard-Reason-8B

Text Generation • 8B • Updated 7 days ago • 100

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

0.8B • Updated 7 days ago • 172 • 2

phecy 

updated a model about 1 month ago

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

0.8B • Updated 7 days ago • 172 • 2

phecy 

published 2 models about 1 month ago

Alibaba-AAIG/YuFeng-XGuard-Reason-0.6B

0.8B • Updated 7 days ago • 172 • 2

Alibaba-AAIG/YuFeng-XGuard-Reason-8B

Text Generation • 8B • Updated 7 days ago • 100

jiaxiaojunQAQ 

authored a paper 2 months ago

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation

Paper • 2512.06589 • Published Dec 6, 2025 • 19

Yuanxh 

updated a model 4 months ago

Alibaba-AAIG/Octopus-SEval-14B

15B • Updated Oct 14, 2025 • 52 • 5

goen-kkk 

updated a dataset 4 months ago

Alibaba-AAIG/StreamGuardBench

Viewer • Updated Oct 9, 2025 • 268k • 51

Yuanxh 

published a model 4 months ago

Alibaba-AAIG/Octopus-SEval-14B

15B • Updated Oct 14, 2025 • 52 • 5

goen-kkk 

published a dataset 4 months ago

Alibaba-AAIG/StreamGuardBench

Viewer • Updated Oct 9, 2025 • 268k • 51

jiaxiaojunQAQ 

authored 3 papers 9 months ago

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery

Paper • 2505.21499 • Published May 27, 2025 • 2

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

Paper • 2505.21494 • Published May 27, 2025 • 8

AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models

Paper • 2505.16211 • Published May 22, 2025 • 18