paper-with-me

Papers

Neural Network Branching for Neural Network Verification

2019-12-03 · ICLR 2020 1 · Jingyue Lu, M. Pawan Kumar

Formal verification of neural networks is essential for their deployment in safety-critical areas. Many available formal verification methods have been shown to be instances of a unified Branch and Bound (BaB) formulation. We propose a novel framework for designing an effective branching strategy for BaB. Specifically, we learn a graph neural network (GNN) to imitate the strong branching heuristic behaviour. Our framework differs from previous methods for learning to branch in two main aspects. Firstly, our framework directly treats the neural network we want to verify as a graph input for the GNN. Secondly, we develop an intuitive forward and backward embedding update schedule. Empirically, our framework achieves roughly $50\%$ reduction in both the number of branches and the time required for verification on various convolutional networks when compared to the best available hand-designed branching strategy. In addition, we show that our GNN model enjoys both horizontal and vertical transferability. Horizontally, the model trained on easy properties performs well on properties of increased difficulty levels. Vertically, the model trained on small neural networks achieves similar performance on large neural networks.

📄 PDF Abstract BibTeX arXiv:1912.01329

Code (1)

oval-group/GNN_branching 공식 구현 pytorch

Tasks

Graph Neural Network

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Neural Network Verification with Branch-and-Bound for General Nonlinearities

2024-05-31 · Zhouxing Shi, Qirui Jin, Zico Kolter, Suman Jana 외

Branch-and-bound (BaB) is among the most effective techniques for neural network (NN) verification. However, existing works on BaB for NN verification have mostly focused on NNs with piecewise linear activations, especia…

E-Globe: Scalable $ε$-Global Verification of Neural Networks via Tight Upper Bounds and Pattern-Aware Branching

2026-02-04 · Wenting Li, Saif R. Kazi, Russell Bent, Duo Zhou 외 arxiv

Neural networks achieve strong empirical performance, but robustness concerns still hinder deployment in safety-critical applications. Formal verification provides robustness guarantees, but current methods face a scalab…

Neural Network Branch-and-Bound for Neural Network Verification

2021-07-27 · Florian Jaeckle, Jingyue Lu, M. Pawan Kumar

Many available formal verification methods have been shown to be instances of a unified Branch-and-Bound (BaB) formulation. We propose a novel machine learning framework that can be used for designing an effective branch…

valid

Privacy-Preserving Robustness Verification for Neural Networks

2026-07-06 · Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie 외 arxiv

Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual pr…

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition

2021-04-14 · Alessandro De Palma, Rudy Bunel, Alban Desmaison, Krishnamurthy Dvijotham 외

We improve the scalability of Branch and Bound (BaB) algorithms for formally proving input-output properties of neural networks. First, we propose novel bounding algorithms based on Lagrangian Decomposition. Previous wor…

Adversarial RobustnessGPU