mlsanityData to 14 Oct 2026

VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch

arXiv 2211.09945 ↗First posted 17 Nov 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

AI's widespread integration has led to neural networks (NNs) deployment on edge and similar limited-resource platforms for safety-critical scenarios. Yet, NN's fragility raises concerns about reliable inference. Moreover, constrained platforms demand compact networks. This study introduces VeriCompress, a tool that automates the search and training of compressed models with robustness guarantees. These models are well-suited for safety-critical applications and adhere to predefined architecture and size limitations, making them deployable on resource-restricted platforms. The method trains models 2-3 times faster than the state-of-the-art approaches, surpassing relevant baseline approaches by average accuracy and robustness gains of 15.1 and 9.8 percentage points, respectively. When deployed on a resource-restricted generic platform, these models require 5-8 times less memory and 2-4 times less inference time than models used in verified robustness literature. Our comprehensive evaluation across various model architectures and datasets, including MNIST, CIFAR, SVHN, and a relevant pedestrian detection dataset, showcases VeriCompress's capacity to identify compressed verified robust models with reduced computation overhead compared to current standards. This underscores its potential as a valuable tool for end users, such as developers of safety-critical applications on edge or Internet of Things platforms, empowering them to create suitable models for safety-critical, resource-constrained platforms in their respective domains.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 45 references that are in the map. First posted on arXiv 17 Nov 2022.

Builds on

21 of 45 references.

References · 21

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  4. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  5. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 583
  6. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  7. 2019Rigging the Lottery: Making All Tickets Winnerscited by 495
  8. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  9. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  10. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 315
  11. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  12. 2018Scaling provable adversarial defensescited by 143
9 more
  1. 2021Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Trainingcited by 110
  2. 2020Gradient Flow in Sparse Neural Networks and How Lottery Tickets Wincited by 77
  3. 2017NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigmcited by 60
  4. 2020Sparse Weight Activation Trainingcited by 45
  5. 2019Fastened CROWN: Tightened Neural Network Robustness Certificatescited by 39
  6. 2019Towards Compact and Robust Deep Neural Networkscited by 23
  7. 2020Fast Geometric Projections for Local Robustness Certificationcited by 21
  8. 2019Verifying Aircraft Collision Avoidance Neural Networks Through Linear Approximations of Safe Regionscited by 9
  9. 2022Networked Online Learning for Control of Safety-Critical Resource-Constrained Systems based on Gaussian Processescited by 2

Built on by

Not cited yet.