{"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/a-few-large-shifts-layer-inconsistency-based","title":"A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection","arxiv_id":"2505.12586","date":"2025-05-19","proceeding":null,"authors":["Sanggeon Yun","Ryozo Masukawa","Hyunwoo Oh","Nathaniel D. Bastian","Mohsen Imani"],"abstract":"Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle, imperceptible perturbations that can lead to incorrect predictions. While detection-based defenses offer a practical alternative to adversarial training, many existing methods depend on external models, complex architectures, heavy augmentations, or adversarial data, limiting their efficiency and generalizability. We introduce a lightweight, plug-in detection framework that leverages internal layer-wise inconsistencies within the target model itself, requiring only benign data for calibration. Our approach is grounded in the A Few Large Shifts Assumption, which posits that adversarial perturbations typically induce large representation shifts in a small subset of layers. Building on this, we propose two complementary strategies--Recovery Testing (RT) and Logit-layer Testing (LT)--to expose internal disruptions caused by adversaries. Evaluated on CIFAR-10, CIFAR-100, and ImageNet under both standard and adaptive threat models, our method achieves state-of-the-art detection performance with negligible computational overhead and no compromise to clean accuracy.","url_abs":"https://arxiv.org/abs/2505.12586v2","url_pdf":"https://arxiv.org/pdf/2505.12586v2.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":"a-few-large-shifts-layer-inconsistency-based","repo_url":"https://github.com/c0510gy/AFLS-AED","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"adversarial-attack-detection","task_name":"Adversarial Attack Detection"},{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}