CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers

• URL: http://arxiv.org/abs/2608.04035v1
• Date: Mon, 03 Aug 2026 07:56:50 GMT
• Title: CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers
• Abstract summary: This work comprehensively evaluates the reliability of Vision Transformers (ViTs) in safety-critical applications.<n>We present CheckOne, a novel, cost-effective method for fault detection and mitigation in ViTs.
• Score: 0.254890465057467
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The wide adoption of Vision Transformers (ViTs) in safety-critical applications raises reliability concerns related to hardware faults. Algorithm-Based Fault Tolerance (ABFT) methods have emerged as lightweight and symmetric protection mechanisms for DNNs. However, they are particularly challenging for ViTs due to their significant computational requirements. This work comprehensively evaluates the reliability of ViTs, emphasizing the need for symmetric protection in their layers. Furthermore, we present CheckOne, a novel, cost-effective method for fault detection and mitigation in ViTs that significantly reduces the computational cost compared to conventional ABFT. Through extensive experiments with multiple ViTs, CheckOne mitigates critical faults by up to $26\times$ and achieves an average 3.8x higher performance than ABFT in ViTs.

Related papers

• MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs [5.317090645596605]
  token pruning is widely used to reduce computational cost without impacting accuracy.<n> adversaries have developed targeted attacks against said token pruning techniques to undermine such attempts to make ViTs efficient.<n>We propose MOAT, a model-agnostic pre-processing defense pipeline that applies a combination of input transformations to protect efficient ViT implementations.
  arXiv  Detail & Related papers  (2026-08-05T10:47:58Z)
• Efficient Adversarial Training via Criticality-Aware Fine-Tuning [59.84340722595335]
  Criticality-Aware Adversarial Training (CAAT) is a novel method that adaptively allocates resources to the most robustness-critical parameters.<n>CAAT incurs only a 4.3% decrease in adversarial robustness while tuning approximately 6% of its parameters.<n>Experiments on three widely used adversarial learning datasets demonstrate that CAAT outperforms state-of-the-art lightweight AT methods with fewer trainable parameters.
  arXiv  Detail & Related papers  (2026-04-14T14:17:38Z)
• Zero Memory Overhead Approach for Protecting Vision Transformer Parameters [0.0]
  A fault tolerance technique is introduced to protect ViT parameters against bit-flip faults with zero memory overhead.<n>When faults are detected, affected parameters are masked by zeroing out, as most parameters in ViT models are near zero.<n>This approach enhances reliability across ViT models, improving the robustness of parameters to bit-flips by up to three orders of magnitude.
  arXiv  Detail & Related papers  (2025-07-04T21:32:24Z)
• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning [69.72249695674665]
  We propose a robust test-time prompt tuning (R-TPT) for vision-language models (VLMs)<n>R-TPT mitigates the impact of adversarial attacks during the inference stage.<n>We introduce a plug-and-play reliability-based weighted ensembling strategy to strengthen the defense.
  arXiv  Detail & Related papers  (2025-04-15T13:49:31Z)
• Exploring Self-Supervised Vision Transformers for Deepfake Detection: A Comparative Analysis [38.074487843137064]
  This paper investigates the effectiveness of self-supervised pre-trained vision transformers (ViTs) compared to supervised pre-trained ViTs and conventional neural networks (ConvNets) for detecting facial deepfake images and videos. It examines their potential for improved generalization and explainability, especially with limited training data. By leveraging SSL ViTs for deepfake detection with modest data and partial fine-tuning, we find comparable adaptability to deepfake detection and explainability via the attention mechanism.
  arXiv  Detail & Related papers  (2024-05-01T07:16:49Z)
• MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection [54.545054873239295]
  Deepfakes have recently raised significant trust issues and security concerns among the public.<n>ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance.<n>This work introduces Mixture-of-Experts modules for Face Forgery Detection (MoE-FFD), a generalized yet parameter-efficient ViT-based approach.
  arXiv  Detail & Related papers  (2024-04-12T13:02:08Z)
• I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization [70.5455407146695]
  We introduce I&S-ViT, a novel method that regulates the PTQ of ViTs in an inclusive and stable fashion.<n>I&S-ViT elevates the performance of 3-bit ViT-B by an impressive 50.68%.
  arXiv  Detail & Related papers  (2023-11-16T13:07:47Z)
• Soft Error Reliability Analysis of Vision Transformers [14.132398744731635]
  Vision Transformers (ViTs) that leverage self-attention mechanism have shown superior performance on many classical vision tasks. Existing ViTs works mainly optimize performance and accuracy, but ViTs reliability issues induced by soft errors have generally been overlooked. In this work, we study the reliability of ViTs and investigate the vulnerability from different architecture granularities.
  arXiv  Detail & Related papers  (2023-02-21T06:17:40Z)
• HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers [35.92244135055901]
  HeatViT is an image-adaptive token pruning framework for vision transformers (ViTs) on embedded FPGAs. HeatViT can achieve 0.7%$sim$8.9% higher accuracy compared to existing ViT pruning studies. HeatViT can achieve more than 28.4%$sim computation reduction, for various widely used ViTs.
  arXiv  Detail & Related papers  (2022-11-15T13:00:43Z)
• Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [56.87383229709899]
  We develop an information rectification module (IRM) and a distribution guided distillation scheme for fully quantized vision transformers (Q-ViT) Our method achieves a much better performance than the prior arts.
  arXiv  Detail & Related papers  (2022-10-13T04:00:29Z)
• Global Vision Transformer Pruning with Hessian-Aware Saliency [93.33895899995224]
  This work challenges the common design philosophy of the Vision Transformer (ViT) model with uniform dimension across all the stacked blocks in a model stage. We derive a novel Hessian-based structural pruning criteria comparable across all layers and structures, with latency-aware regularization for direct latency reduction. Performing iterative pruning on the DeiT-Base model leads to a new architecture family called NViT (Novel ViT), with a novel parameter that utilizes parameters more efficiently.
  arXiv  Detail & Related papers  (2021-10-10T18:04:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.