{"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/recurrent-attention-model-with-log-polar","title":"Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks","arxiv_id":"2002.05388","date":"2020-02-13","proceeding":null,"authors":["Taro Kiritani","Koji Ono"],"abstract":"Convolutional neural networks are vulnerable to small $\\ell^p$ adversarial attacks, while the human visual system is not. Inspired by neural networks in the eye and the brain, we developed a novel artificial neural network model that recurrently collects data with a log-polar field of view that is controlled by attention. We demonstrate the effectiveness of this design as a defense against SPSA and PGD adversarial attacks. It also has beneficial properties observed in the animal visual system, such as reflex-like pathways for low-latency inference, fixed amount of computation independent of image size, and rotation and scale invariance. The code for experiments is available at https://gitlab.com/exwzd-public/kiritani_ono_2020.","url_abs":"https://arxiv.org/abs/2002.05388v1","url_pdf":"https://arxiv.org/pdf/2002.05388v1.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":"recurrent-attention-model-with-log-polar","repo_url":"https://gitlab.com/exwzd-public/kiritani_ono_2020","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"recurrent-attention-model-with-log-polar","repo_url":"https://github.com/wangxiao5791509/RAM-LPM-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.05388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}