Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

[2608.15115] Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2608.15115 (cs) [Submitted on 15 Aug 2026] Title: Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples Authors: Kaisheng Liang , Yiming Cao , Bin Xiao View a PDF of the paper titled Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples, by Kaisheng Liang and 2 other authors View PDF HTML (experimental) Abstract: Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely on local operations with limited degrees of freedom (DOF), such as block-wise shuffling and resizing, overlooking global perspective transformations that naturally arise from viewpoint changes. In this work, we propose a Perspective-Invariant Attack (PIA), which introduces a multi-DOF vertex sampling strategy that systematically covers the perspective transformation hierarchy from 2-DOF translation to 8-DOF projective mapping. By generating geometrically diverse input variations, PIA effectively reduces overfitting of adversarial perturbations to the surrogate model, thereby improving adversarial transferability. We further propose PIA-Mix, a generic extension that maintains a complementary transformation pool and efficiently combines our perspective transformation with auxiliary methods for improved transferability. Extensive experiments involving various DNN architectures, advanced defense mechanisms, and multimodal large language models (LLMs) demonstrate that PIA and PIA-Mix outperform state-of-the-art transfer-based attacks. Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.15115 [cs.CV] (or arXiv:2608.15115v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.15115 Focus to learn more arXiv-issued DOI via DataCite Journal reference: IEEE Transactions on Information Forensics and Security, vol. 21, pp. 6818-6831, 2026 Related DOI : https://doi.org/10.1109/TIFS.2026.3714109 Focus to learn more DOI(s) linking to related resources Submission history From: Kaisheng Liang [ view email ] [v1] Sat, 15 Aug 2026 08:32:22 UTC (1,004 KB) Full-text links: Access Paper: View a PDF of the paper titled Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples, by Kaisheng Liang and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples#611065
• ViTViz: analyzing attention redistribution under adversarial attacks in vision transformers#453375
• Feature Separation and Recalibration for Adversarial Robustness#464535
• Generating Adversarial Examples with Adversarial Networks#199604
• The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks#1123137