{"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/stochastic-activation-pruning-for-robust","title":"Stochastic Activation Pruning for Robust Adversarial Defense","arxiv_id":"1803.01442","date":"2018-03-05","proceeding":"ICLR 2018 1","authors":["Guneet S. Dhillon","Kamyar Azizzadenesheli","Zachary C. Lipton","Jeremy Bernstein","Jean Kossaifi","Aran Khanna","Anima Anandkumar"],"abstract":"Neural networks are known to be vulnerable to adversarial examples. Carefully\nchosen perturbations to real images, while imperceptible to humans, induce\nmisclassification and threaten the reliability of deep learning systems in the\nwild. To guard against adversarial examples, we take inspiration from game\ntheory and cast the problem as a minimax zero-sum game between the adversary\nand the model. In general, for such games, the optimal strategy for both\nplayers requires a stochastic policy, also known as a mixed strategy. In this\nlight, we propose Stochastic Activation Pruning (SAP), a mixed strategy for\nadversarial defense. SAP prunes a random subset of activations (preferentially\npruning those with smaller magnitude) and scales up the survivors to\ncompensate. We can apply SAP to pretrained networks, including adversarially\ntrained models, without fine-tuning, providing robustness against adversarial\nexamples. Experiments demonstrate that SAP confers robustness against attacks,\nincreasing accuracy and preserving calibration.","url_abs":"http://arxiv.org/abs/1803.01442v1","url_pdf":"http://arxiv.org/pdf/1803.01442v1.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":"stochastic-activation-pruning-for-robust","repo_url":"https://github.com/Guneet-Dhillon/Stochastic-Activation-Pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"adversarial-defense","task_name":"Adversarial Defense"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.01442","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}