# Direction-Aggregated Attack for Transferable Adversarial Examples Source: [Direction-Aggregated Attack for Transferable Adversarial Examples]() Collection index: [llms.txt]() Data updated: 2025-10-25T23:50:06.694Z Authors: Tianjin Huang, Vlado Menkovski, Yulong Pei, YuHao Wang, Mykola Pechenizkiy Published: 2021-04-19T09:54:56.000Z ## Abstract Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters are available. Finding adversarial examples that are transferable to other models or developed in a black-box setting is significantly more difficult. In this paper, we propose the Direction-Aggregated adversarial attacks that deliver transferable adversarial examples. Our method utilizes aggregated direction during the attack process for avoiding the generated adversarial examples overfitting to the white-box model. Extensive experiments on ImageNet show that our proposed method improves the transferability of adversarial examples significantly and outperforms state-of-the-art attacks, especially against adversarial robust models. The best averaged attack success rates of our proposed method reaches 94.6\\% against three adversarial trained models and 94.8\\% against five defense methods. It also reveals that current defense approaches do not prevent transferable adversarial attacks. ## 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]() [PDF]()