Certified Interpretability Robustness for Class Activation Mapping
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 25 references that are in the map. First posted on arXiv 26 Jan 2023.
Builds on
22 of 25 references.
References · 22
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2013Intriguing properties of neural networkscited by 5,155
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2015Learning Deep Features for Discriminative Localizationcited by 2,436
- 2016Adversarial examples in the physical worldcited by 1,769
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2017SmoothGrad: removing noise by adding noisecited by 1,109
- 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
- 2017Interpretation of Neural Networks is Fragilecited by 444
- 2018On the Robustness of Interpretability Methodscited by 314
10 more
- 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
- 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
- 2019Simple Black-box Adversarial Attackscited by 251
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 179
- 2020Exactly Computing the Local Lipschitz Constant of ReLU Networkscited by 102
- 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
- 2019Certifiably Robust Interpretation in Deep Learningcited by 35
- 2018RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applicationscited by 27
- 2020End-to-end Autonomous Driving Perception with Sequential Latent Representation Learningcited by 11
- 2019Analyzing the Interpretability Robustness of Self-Explaining Modelscited by 5
Built on by
Citing papers per year: 2023: 1.
1 paper.