Fast Test-Time Refinement for Robust Learned Image Compression

[2608.15113] Fast Test-Time Refinement for Robust Learned Image Compression 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:2608.15113 (cs) [Submitted on 15 Aug 2026] Title: Fast Test-Time Refinement for Robust Learned Image Compression Authors: Jiaming Liang , Chi-Man Pun , Weisi Lin View a PDF of the paper titled Fast Test-Time Refinement for Robust Learned Image Compression, by Jiaming Liang and 2 other authors View PDF HTML (experimental) Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings. However, the high representational capacity endowed by deep neural networks (DNNs) comes at the expense of increased adversarial vulnerability. This hinders their adoption as trusted standardized codecs. Recent work has sketched test-time refinement (TTR) as a defense in gray-box scenarios, despite its original purpose of improving benign RD performance. Unfortunately, extensive iterations of TTR incur prohibitive overhead, while the robustness mechanism lacks theoretical understanding. Moreover, TTR has not been evaluated in white-box settings or against attacks beyond $\ell_2$-bounded rate and untargeted distortion objectives. To bridge these gaps, we present a systematic study. Our study reveals an Asymmetric Adversarial Trajectory (AAT) property in LIC systems: transitioning from adversarial to benign regions is significantly easier than the reverse process, where adversarial examples can often be roughly recovered within only 1-2 steps. We provide a two-dimensional Tube Model to explain this phenomenon. Based on AAT, we propose a Fast Test-Time Refinement (FTTR) framework for practical and robust LIC systems. We establish that the robustness arises from the contraction of adversarial regions induced by the Input-as-Label property of LIC systems, rather than from obfuscated gradients. Extensive evaluations with diverse strong adaptive attacks across multiple LIC systems demonstrate the promise of the proposed FTTR framework. The code is available at this https URL . Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2608.15113 [cs.CV] (or arXiv:2608.15113v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.15113 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jiaming Liang [ view email ] [v1] Sat, 15 Aug 2026 08:30:56 UTC (25,682 KB) Full-text links: Access Paper: View a PDF of the paper titled Fast Test-Time Refinement for Robust Learned Image Compression, by Jiaming 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 cs.AI cs.LG 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

• Fast Test-Time Refinement for Robust Learned Image Compression#611063
• Optimizing Multiple Feature Types for Image Inpainting in the Linear and Nonlinear Setting#1105083
• Context-Aware Mutual Learning for Blind Image Inpainting and Beyond#1083872
• IPsec Extensions to Support Robust Header Compression over IPsec#501237
• ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning#451316