Robustness Certification with Refinement
We present a novel approach for verification of neural networks which combines scalable over-approximation methods with precise (mixed integer) linear programming. This results in significantly better precision than state of the art verifiers on feed forward neural networks with piecewise linear activation functions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding
The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input pe…
Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples
In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications ca…
Incremental Randomized Smoothing Certification
Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifie…
A Tool for Neural Network Global Robustness Certification and Training
With the increment of interest in leveraging machine learning technology in safety-critical systems, the robustness of neural networks under external disturbance receives more and more concerns. Global robustness is a ro…
GPUAre Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications
A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation…