paper-with-me

Papers

Certified Interpretability Robustness for Class Activation Mapping

2023-01-26 · Alex Gu, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel

Interpreting machine learning models is challenging but crucial for ensuring the safety of deep networks in autonomous driving systems. Due to the prevalence of deep learning based perception models in autonomous vehicles, accurately interpreting their predictions is crucial. While a variety of such methods have been proposed, most are shown to lack robustness. Yet, little has been done to provide certificates for interpretability robustness. Taking a step in this direction, we present CORGI, short for Certifiably prOvable Robustness Guarantees for Interpretability mapping. CORGI is an algorithm that takes in an input image and gives a certifiable lower bound for the robustness of the top k pixels of its CAM interpretability map. We show the effectiveness of CORGI via a case study on traffic sign data, certifying lower bounds on the minimum adversarial perturbation not far from (4-5x) state-of-the-art attack methods.

📄 PDF Abstract BibTeX arXiv:2301.11324

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingAutonomous Vehicles

Methods 이 논문이 사용한 방법론

CAM Class activation maps could be used to interpret the prediction decision made by the convolutional neural network (CNN). Image source: [Learning Deep Features for…

Similar Papers 제목 키워드 기반

Efficient Neural Network Robustness Certification with General Activation Functions

2018-11-02 · NeurIPS 2018 12 · Huan Zhang, Tsui-Wei Weng, Pin-Yu Chen, Cho-Jui Hsieh 외

Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem. Nevertheless, recently it has been shown to be p…

Computational EfficiencyEfficient Neural Network

Lipschitz-aware Linearity Grafting for Certified Robustness

2025-10-29 · Yongjin Han, Suhyun Kim arxiv

Lipschitz constant is a fundamental property in certified robustness, as smaller values imply robustness to adversarial examples when a model is confident in its prediction. However, identifying the worst-case adversaria…

Interpreting Adversarial Examples by Activation Promotion and Suppression

2019-04-03 · Kaidi Xu, Sijia Liu, Gaoyuan Zhang, Mengshu Sun 외

It is widely known that convolutional neural networks (CNNs) are vulnerable to adversarial examples: images with imperceptible perturbations crafted to fool classifiers. However, interpretability of these perturbations i…

Adversarial Robustness

DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation

2023-05-22 · Haitham Khedr, Yasser Shoukry

Formal certification of Neural Networks (NNs) is crucial for ensuring their safety, fairness, and robustness. Unfortunately, on the one hand, sound and complete certification algorithms of ReLU-based NNs do not scale to …

Adversarial RobustnessFairness

Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective

2022-10-04 · Bohang Zhang, Du Jiang, Di He, LiWei Wang

Designing neural networks with bounded Lipschitz constant is a promising way to obtain certifiably robust classifiers against adversarial examples. However, the relevant progress for the important $\ell_\infty$ perturbat…

Robust classification