Independently optimized decoy patches redirect ViT attention-based defenses away from true adversarial regions while largely preserving attack success.
Attention is all you need
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
GDLA delivers state-of-the-art accuracy on CT, MRI, ultrasound and dermoscopy segmentation benchmarks while keeping linear O(N) complexity in a PVT encoder-decoder.
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
A method learns synthetic-to-real parameter corrections from source languages and transfers them to target languages without any real target data, improving HTR across five languages and six models.
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.
GRACE improves ID accuracy by 10.8% and adversarial accuracy by 13.5% on ImageNet-tuned CLIP while holding OOD accuracy near the zero-shot baseline.
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
citing papers explorer
-
Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT
Independently optimized decoy patches redirect ViT attention-based defenses away from true adversarial regions while largely preserving attack success.
-
Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation
GDLA delivers state-of-the-art accuracy on CT, MRI, ultrasound and dermoscopy segmentation benchmarks while keeping linear O(N) complexity in a PVT encoder-decoder.
-
A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions
DBAC is a new directional metric for bias amplification in image captions that is less sensitive to sentence encoders and more accurate than LIC, validated on COCO gender and race attributes.
-
Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies
A method learns synthetic-to-real parameter corrections from source languages and transfers them to target languages without any real target data, improving HTR across five languages and six models.
-
Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.
-
The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models
GRACE improves ID accuracy by 10.8% and adversarial accuracy by 13.5% on ImageNet-tuned CLIP while holding OOD accuracy near the zero-shot baseline.
-
PVeRA: Probabilistic Vector-Based Random Matrix Adaptation
PVeRA extends VeRA by making its frozen random low-rank matrices probabilistic, enabling better handling of ambiguities and outperforming prior adapters on the VTAB-1k benchmark.
- TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting