{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interpretability-guided-test-time-adversarial","title":"Interpretability-Guided Test-Time Adversarial Defense","arxiv_id":"2409.15190","date":"2024-09-23","proceeding":null,"authors":["Akshay Kulkarni","Tsui-Wei Weng"],"abstract":"We propose a novel and low-cost test-time adversarial defense by devising interpretability-guided neuron importance ranking methods to identify neurons important to the output classes. Our method is a training-free approach that can significantly improve the robustness-accuracy tradeoff while incurring minimal computational overhead. While being among the most efficient test-time defenses (4x faster), our method is also robust to a wide range of black-box, white-box, and adaptive attacks that break previous test-time defenses. We demonstrate the efficacy of our method for CIFAR10, CIFAR100, and ImageNet-1k on the standard RobustBench benchmark (with average gains of 2.6%, 4.9%, and 2.8% respectively). We also show improvements (average 1.5%) over the state-of-the-art test-time defenses even under strong adaptive attacks.","url_abs":"https://arxiv.org/abs/2409.15190v1","url_pdf":"https://arxiv.org/pdf/2409.15190v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"interpretability-guided-test-time-adversarial","repo_url":"https://github.com/Trustworthy-ML-Lab/Interpretability-Guided-Defense","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.15190","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}