{"type":"ScholarlyArticle","title":"PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN (Extended Abstract)","authors":[{"name":"Jiayu Zhang","slug":"jiayu-zhang","given":"Jiayu","family":"Zhang","affiliation":""},{"name":"Zhiyu Zhu","slug":"zhiyu-zhu","given":"Zhiyu","family":"Zhu","affiliation":""},{"name":"Xinyi Wang","slug":"xinyi-wang","given":"Xinyi","family":"Wang","affiliation":""},{"name":"Silin Liao","slug":"silin-liao","given":"Silin","family":"Liao","affiliation":""},{"name":"Zhibo Jin","slug":"zhibo-jin","given":"Zhibo","family":"Jin","affiliation":""},{"name":"Flora Salim","slug":"flora-salim","given":"Flora","family":"Salim","affiliation":""},{"name":"Huaming Chen","slug":"huaming-chen","given":"Huaming","family":"Chen","affiliation":""}],"abstract":"Deep neural networks are vulnerable to adversarial examples, posing serious security risks. While GAN-based attacks such as AdvGAN enable fast adversarial example generation, they typically operate in a single step, limiting attack effectiveness and transferability. In this work, we propose PAR-AdvGAN, a progressive auto-regressive GAN framework that iteratively refines adversarial perturbations. By conditioning each iteration on the previous output, PAR-AdvGAN produces stronger, more transferable attacks while maintaining low visual distortion and high generation speed. Experiments on multiple models and datasets demonstrate that PAR-AdvGAN significantly outperforms baseline methods in attack success rate, achieving up to 335.5 frames per second, highlighting its practical efficiency for black-box attack scenarios.","doi":"10.24963/ijcai.2026/930","url":"https://ijcai.org/proceedings/2026/930","pdf":"https://ijcai.org/proceedings/2026/0930.pdf","markdown":"https://ijcai.org/proceedings/2026/930.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/930","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":930,"pages":{"first":8301,"last":8305},"keywords":["Machine Learning: Trustworthy machine learning","AI Ethics, Trust, Fairnes: Trustworthy AI","AI Ethics, Trust, Fairnes: Safety and robustness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}