# CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers

arXiv: https://arxiv.org/abs/2608.04035 · HTML: https://mlsanity.com/paper/2608.04035/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks](https://mlsanity.com/paper/2305.05750/) (2023)
- [FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks](https://mlsanity.com/paper/2003.12203/) (2020)
- [ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training](https://mlsanity.com/paper/2410.11720/) (2024)
- [FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention](https://mlsanity.com/paper/2504.02211/) (2025)
- [ALBERTA: ALgorithm-Based Error Resilience in Transformer Architectures](https://mlsanity.com/paper/2310.03841/) (2023)
- [Custom Algorithm-based Fault Tolerance for Attention Layers in Transformers](https://mlsanity.com/paper/2507.16676/) (2025)
- [Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs](https://mlsanity.com/paper/2605.07417/) (2026)
- [In Transformer We Trust? A Perspective on Transformer Architecture Failure Modes](https://mlsanity.com/paper/2602.14318/) (2026)

## Abstract (arXiv)

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× and achieves an average 3.8x higher performance than ABFT in ViTs.