STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs

Dimensions overall score 7.0

• STRAP-ViT is a plug-and-play defense mechanism that enhances Vision Transformers' robustness against adversarial patches without additional training. In this paper, we claim that the tokens which correspond to the areas of the image that contain the adversarial noise, have different statistical properties when compared to the tokens which do not overlap with the adversarial perturbations.problem 35%
  Evidencepartial

  STRAP-ViT is a plug-and-play defense mechanism that enhances Vision Transformers' robustness against adversarial patches without additional training. In this paper, we claim that the tokens which correspond to the areas of the image that contain the adversarial noise, have different statistical properties when compared to the tokens which do not overlap with the adversarial perturbations.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• Adversarial patches are physically realizable localized noise, which are able to hijack Vision Transformers (ViT) self-attention, pulling focus toward a small, high-contrast region and corrupting the class token to force confident misclassifications. In this paper, we claim that the tokens which correspond to the areas of the image that contain the adversarial noise, have different statistical properties when compared to the tokens which do not overlap with the adversarial perturbations.method 35%
  Evidencepartial

  Adversarial patches are physically realizable localized noise, which are able to hijack Vision Transformers (ViT) self-attention, pulling focus toward a small, high-contrast region and corrupting the class token to force confident misclassifications. In this paper, we claim that the tokens which correspond to the areas of the image that contain the adversarial noise, have different statistical properties when compared to the tokens which do not overlap with the adversarial perturbations.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• ScienceToStartup currently rates this 7.0/10 on the public viability pass. STRAP-ViT has been tested on multiple pre-trained vision transformer architectures (ViT-base-16 and DinoV2) and datasets (ImageNet and CalTech-101), across multiple adversarial attacks (Adversarial Patch, LAVAN, GDPA and RP2), and found to provide excellent robust accuracies lying within a 2-3% range of the clean baselines, and outperform the state-of-the-art.result 35%
  Evidencepartial

  ScienceToStartup currently rates this 7.0/10 on the public viability pass. STRAP-ViT has been tested on multiple pre-trained vision transformer architectures (ViT-base-16 and DinoV2) and datasets (ImageNet and CalTech-101), across multiple adversarial attacks (Adversarial Patch, LAVAN, GDPA and RP2), and found to provide excellent robust accuracies lying within a 2-3% range of the clean baselines, and outperform the state-of-the-art.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

• Adversarial Defense moved forward this cycle; last verified April 2026. Public score 7.0/10.why now 35%
  Evidencepartial

  Adversarial Defense moved forward this cycle; last verified April 2026. Public score 7.0/10.

  Implicationpartial

  Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.

  Verificationpartial

  partial

Competitive landscape

STRAP-ViT is a plug-and-play defense mechanism that enhances Vision Transformers' robustness against adversarial patches without additional training.