paper-with-me

홈 › Papers

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions

2025-04-02 · Tahmid Hasan Prato, Seijoon Kim, Lizhong Chen, Sanghyun Hong

Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%, and in the worst cases, up to 99%. This susceptibility poses great challenges in deploying models on computing platforms, where adversaries can induce bit-flips through software or bitwise corruptions may occur naturally. Most prior work addresses this issue with hardware or system-level approaches, such as integrating additional hardware components to verify a model's integrity at inference. However, these methods have not been widely deployed as they require infrastructure or platform-wide modifications. In this paper, we propose a new approach to addressing this issue: training models to be more resilient to bitwise corruptions to their parameters. Our approach, Hessian-aware training, promotes models with $flatter$ loss surfaces. We show that, while there have been training methods, designed to improve generalization through Hessian-based approaches, they do not enhance resilience to parameter corruptions. In contrast, models trained with our method demonstrate increased resilience to parameter corruptions, particularly with a 20$-$50% reduction in the number of bits whose individual flipping leads to a 90$-$100% accuracy drop. Moreover, we show the synergy between ours and existing hardware and system-level defenses.

📄 PDF Abstract BibTeX arXiv:2504.01933

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The asymptotic spectrum of the Hessian of DNN throughout training

2019-10-01 · ICLR 2020 1 · Arthur Jacot, Franck Gabriel, Clément Hongler

The dynamics of DNNs during gradient descent is described by the so-called Neural Tangent Kernel (NTK). In this article, we show that the NTK allows one to gain precise insight into the Hessian of the cost of DNNs. When …

FitAct: Error Resilient Deep Neural Networks via Fine-Grained Post-Trainable Activation Functions

2021-12-27 · Behnam Ghavami, Mani Sadati, Zhenman Fang, Lesley Shannon

Deep neural networks (DNNs) are increasingly being deployed in safety-critical systems such as personal healthcare devices and self-driving cars. In such DNN-based systems, error resilience is a top priority since faults…

Self-Driving Cars

Enhancing Fault Resilience of QNNs by Selective Neuron Splitting

2023-06-16 · Mohammad Hasan Ahmadilivani, Mahdi Taheri, Jaan Raik, Masoud Daneshtalab 외

The superior performance of Deep Neural Networks (DNNs) has led to their application in various aspects of human life. Safety-critical applications are no exception and impose rigorous reliability requirements on DNNs. Q…

On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

2020-06-03 · Matilde Gargiani, Andrea Zanelli, Moritz Diehl, Frank Hutter

Following early work on Hessian-free methods for deep learning, we study a stochastic generalized Gauss-Newton method (SGN) for training DNNs. SGN is a second-order optimization method, with efficient iterations, that we…

Second-order methods

eFAT: Improving the Effectiveness of Fault-Aware Training for Mitigating Permanent Faults in DNN Hardware Accelerators

2023-04-20 · Muhammad Abdullah Hanif, Muhammad Shafique

Fault-Aware Training (FAT) has emerged as a highly effective technique for addressing permanent faults in DNN accelerators, as it offers fault mitigation without significant performance or accuracy loss, specifically at …