# On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm

Source: [On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm](<https://www.sota2.com/research/paper/68fa64f51e209131cea07506>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:37.115Z

Authors: Tsui-Wei Weng, Huan Zhang, Pin-Yu Chen, Aurelie Lozano, Cho-Jui Hsieh, Luca Daniel

Published: 2018-10-19T18:44:58.000Z

## Abstract

CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extreme Value Theory (EVT) based robustness score for large-scale deep neural networks (DNNs). In this paper, we propose two extensions on this robustness score. First, we provide a new formal robustness guarantee for classifier functions that are twice differentiable. We apply extreme value theory on the new formal robustness guarantee and the estimated robustness is called second-order CLEVER score. Second, we discuss how to handle gradient masking, a common defensive technique, using CLEVER with Backward Pass Differentiable Approximation (BPDA). With BPDA applied, CLEVER can evaluate the intrinsic robustness of neural networks of a broader class -- networks with non-differentiable input transformations. We demonstrate the effectiveness of CLEVER with BPDA in experiments on a 121-layer Densenet model trained on the ImageNet dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1810.08640>)

[PDF](<https://arxiv.org/pdf/1810.08640.pdf>)