paper-with-me

홈 › Papers

Zero Memory Overhead Approach for Protecting Vision Transformer Parameters

2025-07-04 · Fereshteh Baradaran, Mohsen Raji, Azadeh Baradaran, Arezoo Baradaran, Reihaneh Akbarifard arxiv

Vision Transformers (ViTs) have demonstrated superior performance over Convolutional Neural Networks (CNNs) in various vision-related tasks such as classification, object detection, and segmentation due to their use of self-attention mechanisms. As ViTs become more popular in safety-critical applications like autonomous driving, ensuring their correct functionality becomes essential, especially in the presence of bit-flip faults in their parameters stored in memory. In this paper, a fault tolerance technique is introduced to protect ViT parameters against bit-flip faults with zero memory overhead. Since the least significant bits of parameters are not critical for model accuracy, replacing the LSB with a parity bit provides an error detection mechanism without imposing any overhead on the model. When faults are detected, affected parameters are masked by zeroing out, as most parameters in ViT models are near zero, effectively preventing accuracy degradation. This approach enhances reliability across ViT models, improving the robustness of parameters to bit-flips by up to three orders of magnitude, making it an effective zero-overhead solution for fault tolerance in critical applications.

📄 PDF Abstract BibTeX arXiv:2507.03816

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingObject Detection

Similar Papers 제목 키워드 기반

DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning

2025-10-15 · Omayma Moussadek, Riccardo Salami, Simone Calderara arxiv

Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously acquired knowledge. However, current methods face challenges …

Incremental LearningContinual Learning

Make Shuffling Great Again: A Side-Channel Resistant Fisher-Yates Algorithm for Protecting Neural Networks

2025-01-01 · Leonard Puškáč, Marek Benovič, Jakub Breier, Xiaolu Hou

Neural network models implemented in embedded devices have been shown to be susceptible to side-channel attacks (SCAs), allowing recovery of proprietary model parameters, such as weights and biases. There are already ava…

Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures

2025-10-27 · Gokulnath Rajendran, Suman Deb, Anupam Chattopadhyay arxiv

Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential …

Computational Efficiency

Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs

2026-07-02 · Altay Toktassyn, Jurn-Gyu Park arxiv

Modern pretrained vision models achieve strong accuracy but demand substantial GPU memory for fine-tuning, making edge deployment impractical. This paper compares five parameter-efficient fine-tuning (PEFT) methods (Full…

parameter-efficient fine-tuning

Nanbeige4.2-3B on Apple Silicon: Fixing Deployment Bugs and Decreasing Looped Transformer Memory Overhead

2026-08-14 · John T. Halloran arxiv

Nanbeige4.2-3B is a 3B-parameter agentic model built around a Looped Transformer (LT) that reuses one stack of layers for a second forward pass, adding effective depth without additional parameters. Evaluated on Apple Si…