paper-with-me

홈 › Papers

Using Z3 for Formal Modeling and Verification of FNN Global Robustness

2023-04-20 · Yihao Zhang, Zeming Wei, Xiyue Zhang, Meng Sun

While Feedforward Neural Networks (FNNs) have achieved remarkable success in various tasks, they are vulnerable to adversarial examples. Several techniques have been developed to verify the adversarial robustness of FNNs, but most of them focus on robustness verification against the local perturbation neighborhood of a single data point. There is still a large research gap in global robustness analysis. The global-robustness verifiable framework DeepGlobal has been proposed to identify \textit{all} possible Adversarial Dangerous Regions (ADRs) of FNNs, not limited to data samples in a test set. In this paper, we propose a complete specification and implementation of DeepGlobal utilizing the SMT solver Z3 for more explicit definition, and propose several improvements to DeepGlobal for more efficient verification. To evaluate the effectiveness of our implementation and improvements, we conduct extensive experiments on a set of benchmark datasets. Visualization of our experiment results shows the validity and effectiveness of the approach.

📄 PDF Abstract BibTeX arXiv:2304.10558

Code (1)

weizeming/z3_for_verification_of_fnn_global_robustness 공식 구현 pytorch

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Probably Approximately Global Robustness Certification

2025-11-09 · Peter Blohm, Patrick Indri, Thomas Gärtner, Sagar Malhotra arxiv

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approach…

Adversarial Robustness

Global Robustness Verification Networks

2020-06-08 · Weidi Sun, Yuteng Lu, Xiyue Zhang, Zhanxing Zhu 외

The wide deployment of deep neural networks, though achieving great success in many domains, has severe safety and reliability concerns. Existing adversarial attack generation and automatic verification techniques cannot…

Adversarial Attack

Verifying Global Neural Network Specifications using Hyperproperties

2023-06-21 · David Boetius, Stefan Leue

Current approaches to neural network verification focus on specifications that target small regions around known input data points, such as local robustness. Thus, using these approaches, we can not obtain guarantees for…

Fairness

Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach

2023-12-28 · Jingda Yang, Ying Wang

This paper introduces Auto-modeling of Formal Verification with Real-world Prompting for 5G and NextG protocols (AVRE), a novel system designed for the formal verification of Next Generation (NextG) communication protoco…

Language ModelingLanguage ModellingLarge Language Model

Formal Verification of Deep Neural Networks for Object Detection

2024-07-01 · Yizhak Y. Elboher, Avraham Raviv, Yael Leibovich Weiss, Omer Cohen 외

Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulner…

image-classificationImage ClassificationObjectobject-detection+1