Multi-level Floyd-Steinberg dithering defends DINOv2 and PaliGemma models against PGD, MI-FGSM and SIA attacks on six tasks while causing less clean-input degradation than diffusion denoising or other baselines.
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floyd-Steinberg error-diffusion dithering as a lightweight, model-agnostic input transformation that disrupts adversarial perturbations while preserving semantic content. Unlike prior work, which was limited to binary dithering, grayscale CIFAR-10, and a single small model trained from scratch, we evaluate across six tasks (classification, segmentation, depth estimation, retrieval, captioning, visual question answering), two model families (DINOv2, PaliGemma), and three attacks of increasing strength (PGD, MI-FGSM, SIA), as well as an adaptive attacker using a straight-through estimator. Our results show that Floyd-Steinberg dithering at intermediate quantization levels, especially when combined with post-processing blur, exceeds or matches all tested baselines, including diffusion-based denoising, with substantially less degradation on clean inputs.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
Multi-level Floyd-Steinberg dithering defends DINOv2 and PaliGemma models against PGD, MI-FGSM and SIA attacks on six tasks while causing less clean-input degradation than diffusion denoising or other baselines.