# GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees Source: [GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees]() Collection index: [llms.txt]() Data updated: 2026-04-16T05:00:11.996Z Authors: Arya Shah, Kaveri Visavadiya, Manisha Padala Published: 2026-04-14T14:03:22.000Z ## Abstract Adversarial robustness is essential for deploying neural networks in safety-critical applications, yet standard evaluation methods either require expensive adversarial attacks or report only a single aggregate score that obscures how robustness is distributed across classes. We introduce the \\emph{GF-Score} (GREAT-Fairness Score), a framework that decomposes the certified GREAT Score into per-class robustness profiles and quantifies their disparity through four metrics grounded in welfare economics: the Robustness Disparity Index (RDI), the Normalized Robustness Gini Coefficient (NRGC), Worst-Case Class Robustness (WCR), and a Fairness-Penalized GREAT Score (FP-GREAT). The framework further eliminates the original method's dependence on adversarial attacks through a self-calibration procedure that tunes the temperature parameter using only clean accuracy correlations. Evaluating 22 models from RobustBench across CIFAR-10 and ImageNet, we find that the decomposition is exact, that per-class scores reveal consistent vulnerability patterns (e.g., \`\`cat'' is the weakest class in 76\\% of CIFAR-10 models), and that more robust models tend to exhibit greater class-level disparity. These results establish a practical, attack-free auditing pipeline for diagnosing where certified robustness guarantees fail to protect all classes equally. We release our code on \\href{https://github.com/aryashah2k/gf-score}{GitHub}. ## 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. - [Ranking fidelity evaluation on ImageNet L-inf RobustBench (test)](): Ranking fidelity evaluation; ImageNet L-inf RobustBench (test); Spearman Correlation (ρ): 1. - [Ranking fidelity evaluation on CIFAR-10 L2 RobustBench (test)](): Ranking fidelity evaluation; CIFAR-10 L2 RobustBench (test); Spearman Rank Correlation: 0.871. ## Original sources and implementation [Original paper]() [PDF]()