Configuring BDD compilation techniques for feature models

C Dubslaff, N Husung, N Käfer - … of the 28th ACM International Systems …, 2024 - dl.acm.org
The compilation of feature models into binary decision diagrams (BDDs) is a major
challenge in the area of configurable systems analysis. Many large-scale feature models …

QEBVerif: Quantization error bound verification of neural networks

Y Zhang, F Song, J Sun - International Conference on Computer Aided …, 2023 - Springer
To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge
devices, quantization is widely regarded as one promising technique. It reduces the …

Attack as detection: Using adversarial attack methods to detect abnormal examples

Z Zhao, G Chen, T Liu, T Li, F Song, J Wang… - ACM Transactions on …, 2024 - dl.acm.org
As a new programming paradigm, deep learning (DL) has achieved impressive performance
in areas such as image processing and speech recognition, and has expanded its …

Certified quantization strategy synthesis for neural networks

Y Zhang, G Chen, F Song, J Sun, JS Dong - International Symposium on …, 2024 - Springer
Quantization plays an important role in deploying neural networks on embedded, real-time
systems with limited computing and storage resources (eg, edge devices). It significantly …

An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks

Y Tao, W Liu, F Song, Z Liang, J Wang… - … Symposium on Automated …, 2023 - Springer
Deep neural networks,(DNNs, aka NNs), have been widely used in various tasks and have
been proven to be successful. However, the accompanied expensive computing and …

[BOOK][B] Computer Aided Verification: 35th International Conference, CAV 2023, Paris, France, July 17–22, 2023, Proceedings, Part I

C Enea, A Lal - 2023 - library.oapen.org
The open access proceedings set LNCS 13964, 13965, 13966 constitutes the refereed
proceedings of the 35th International Conference on Computer Aided Verification, CAV …

Static Analysis by Abstract Interpretation of Quantitative Program Properties

D Mazzucato - 2024 - inria.hal.science
This thesis aims to develop efficient, mathematically sound methods to improve software
reliability using abstract interpretation, a formal framework for approximating program …

[PDF][PDF] QEBVerif: Quantization error bound verification of neural networks.(2023)

Y ZHANG, F SONG, J SUN - Proceedings of the 35th …, 2023 - ink.library.smu.edu.sg
To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge
devices, quantization is widely regarded as one promising technique. It reduces the …