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

Sawinder Kaur, Yi Xiao, Asif Salekin

Research output: Contribution to journalConference Articlepeer-review


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.

Original languageEnglish (US)
Pages (from-to)22899-22905
Number of pages7
JournalProceedings of the AAAI Conference on Artificial Intelligence
Issue number21
StatePublished - Mar 25 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: Feb 20 2024Feb 27 2024

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch'. Together they form a unique fingerprint.

Cite this