{"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/deep-neural-networks-are-easily-fooled-high","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","arxiv_id":"1412.1897","date":"2014-12-05","proceeding":"CVPR 2015 6","authors":["Anh Nguyen","Jason Yosinski","Jeff Clune"],"abstract":"Deep neural networks (DNNs) have recently been achieving state-of-the-art\nperformance on a variety of pattern-recognition tasks, most notably visual\nclassification problems. Given that DNNs are now able to classify objects in\nimages with near-human-level performance, questions naturally arise as to what\ndifferences remain between computer and human vision. A recent study revealed\nthat changing an image (e.g. of a lion) in a way imperceptible to humans can\ncause a DNN to label the image as something else entirely (e.g. mislabeling a\nlion a library). Here we show a related result: it is easy to produce images\nthat are completely unrecognizable to humans, but that state-of-the-art DNNs\nbelieve to be recognizable objects with 99.99% confidence (e.g. labeling with\ncertainty that white noise static is a lion). Specifically, we take\nconvolutional neural networks trained to perform well on either the ImageNet or\nMNIST datasets and then find images with evolutionary algorithms or gradient\nascent that DNNs label with high confidence as belonging to each dataset class.\nIt is possible to produce images totally unrecognizable to human eyes that DNNs\nbelieve with near certainty are familiar objects, which we call \"fooling\nimages\" (more generally, fooling examples). Our results shed light on\ninteresting differences between human vision and current DNNs, and raise\nquestions about the generality of DNN computer vision.","url_abs":"http://arxiv.org/abs/1412.1897v4","url_pdf":"http://arxiv.org/pdf/1412.1897v4.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":"deep-neural-networks-are-easily-fooled-high","repo_url":"https://github.com/Evolving-AI-Lab/fooling","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-neural-networks-are-easily-fooled-high","repo_url":"https://github.com/AfuroZamurai/InformatiCup_Leibniz-7","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"evolutionary-algorithms","task_name":"Evolutionary Algorithms"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1412.1897","atlas_url":"https://app.syntology.ai/?focus=1412.1897","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}