List your company

Image-Text Retrieval on Flickr30K (R@1)

100R@1MDCS-SGA
-0.817625.356251.5377.7038Jun 7, 2024Sep 30, 2024Jan 23, 2025May 19, 2025Sep 11, 2025Jan 4, 2026Apr 30, 2026

Evaluation results

MethodLinks
MDCS-SGASource Model=ALBEF, Target Model=ALBEF, Attack Setting=White-box2026.02100
MDCS-SAAETSource Model=TCL, Target Model=TCL, Attack Setting=White-box2026.02100
MDCS-SAAETSource Model=CLIPViT, Target Model=CLIPViT, Attack Setting=White-box2026.02100
MDCS-SAAETSource Model=CLIPCNN, Target Model=CLIPCNN, Attack Setting=White-box2026.02100
MDCS-SAAETSource Model=ALBEF, Target Model=ALBEF, Attack Setting=White-box2026.02100
SGASource Model=CLIPViT, Target Model=CLIPViT, Attack Setting=White-box2026.02100
MDCS-DRASource Model=ALBEF, Target Model=ALBEF, Attack Setting=White-box2026.0299.9
MDCS-SAAETSource Model=ALBEF, Target Model=ALBEF, Attack Setting=White-box2026.0299.9
MDCS-SAAETSource Model=TCL, Target Model=ALBEF, Attack Setting=Black-box2026.0299.17
MDCS-SAAETSource Model=ALBEF, Target Model=TCL, Attack Setting=Black-box2026.0296.71
MDCS-SAAETSource Model=ALBEF, Target Model=TCL, Attack Setting=Black-box2026.0296.52
MDCS-SGASource Model=ALBEF, Target Model=TCL, Attack Setting=Black-box2026.0291.78
SETOKIMSize=7B, Visual Features=semantic-equivalent (SE), Visual Tokens=continuous (C), Observed during training=false2024.0686.9
NEXT-GPTSize=7B, Visual Features=patch-level features (P), Visual Tokens=continuous (C), Observed during training=false2024.0684.5
LaVITSize=7B, Visual Features=patch-level features (P), Visual Tokens=continuous (C), Observed during training=false2024.0683
HQ-CLIPDataset (Data Size)=DataComp-DFN (130M), Samples Seen@Resolution=3.20B@224, GPU-hours=≈ 2675, Zero-shot=true2026.0477.9
EmuSize=7B, Visual Features=learnable queries (Q), Visual Tokens=continuous (C), Observed during training=false2024.0677.4
MetaCLIP-400MDataset (Data Size)=(400M), Samples Seen@Resolution=12.8B@224, GPU-hours=≈ 10700, Zero-shot=true2026.0476.7
ChameleonSize=34B, Visual Features=patch-level features (P), Visual Tokens=discrete (D), Observed during training=false2024.0674.7
OpenCLIPDataset (Data Size)=LAION-400M (400M), Samples Seen@Resolution=12.8B@224, GPU-hours=10736, Zero-shot=true2026.0474.6
DynamiCSDataset (Data Size)=LAION-400M (298M), Samples Seen@Resolution=2.56B@112 + 128M@224, GPU-hours=299, Zero-shot=true2026.0473.9
DynamiCSDataset (Data Size)=LAION-400M (298M), Samples Seen@Resolution=1.28B@112 + 128M@224, GPU-hours=163, Zero-shot=true2026.0472.7
RECLIP*Dataset (Data Size)=LAION-400M (298M), Samples Seen@Resolution=2.56B@112 + 128M@224, GPU-hours=280, Zero-shot=true2026.0472.4
OpenAI-WITDataset (Data Size)=-, Samples Seen@Resolution=12.8B@224, GPU-hours=10700, Zero-shot=true2026.0472.2
CLIPA*Dataset (Data Size)=LAION-400M (298M), Samples Seen@Resolution=2.56B@112 + 128M@224, GPU-hours=269, Zero-shot=true2026.0471.7
DynamiCSDataset (Data Size)=DataComp-DFN (130M), Samples Seen@Resolution=2.56B@112 + 128M@224, GPU-hours=299, Zero-shot=true2026.0471.3
RandomDataset (Data Size)=LAION-400M (298M), Samples Seen@Resolution=1.28B@112 + 128M@224, GPU-hours=151, Zero-shot=true2026.0469.4
DynamiCSDataset (Data Size)=DataComp-DFN (130M), Samples Seen@Resolution=1.28B@112 + 128M@224, GPU-hours=163, Zero-shot=true2026.0469.3
DFN*Dataset (Data Size)=DataComp-DFN (130M), Samples Seen@Resolution=1.28B@112 + 128M@224, GPU-hours=151, Zero-shot=true2026.0468.1
MDCS-SAAETSource Model=ALBEF, Target Model=CLIPCNN, Attack Setting=Black-box2026.0267.89
MDCS-SAAETSource Model=ALBEF, Target Model=CLIPViT, Attack Setting=Black-box2026.0267.01
DynamiCSDataset (Data Size)=DataComp-DFN (130M), Samples Seen@Resolution=0.64B@112 + 128M@224, GPU-hours=95, Zero-shot=true2026.0466.6
DataCompDataset (Data Size)=DataComp-Large (1.28B), Samples Seen@Resolution=1.28B@224, GPU-hours=≈ 1070, Zero-shot=true2026.0463.6
RandomDataset (Data Size)=DataComp-DFN (130M), Samples Seen@Resolution=0.64B@112 + 128M@224, GPU-hours=90, Zero-shot=true2026.0462.3
MDCS-SAAETSource Model=ALBEF, Target Model=CLIPCNN, Attack Setting=Black-box2026.0260.54
MDCS-SAAETSource Model=ALBEF, Target Model=CLIPViT, Attack Setting=Black-box2026.0260.25
PGDSource Model=ALBEF, Target Model=ALBEF, Attack Setting=White-box2026.0252.45
PGDSource Model=ALBEF, Target Model=CLIPCNN, Attack Setting=Black-box2026.0210.34
PGDSource Model=ALBEF, Target Model=CLIPViT, Attack Setting=Black-box2026.028.96
PGDSource Model=ALBEF, Target Model=TCL, Attack Setting=Black-box2026.023.06