{"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/latentpoison-adversarial-attacks-on-the","title":"LatentPoison - Adversarial Attacks On The Latent Space","arxiv_id":"1711.02879","date":"2017-11-08","proceeding":null,"authors":["Antonia Creswell","Anil A. Bharath","Biswa Sengupta"],"abstract":"Robustness and security of machine learning (ML) systems are intertwined,\nwherein a non-robust ML system (classifiers, regressors, etc.) can be subject\nto attacks using a wide variety of exploits. With the advent of scalable deep\nlearning methodologies, a lot of emphasis has been put on the robustness of\nsupervised, unsupervised and reinforcement learning algorithms. Here, we study\nthe robustness of the latent space of a deep variational autoencoder (dVAE), an\nunsupervised generative framework, to show that it is indeed possible to\nperturb the latent space, flip the class predictions and keep the\nclassification probability approximately equal before and after an attack. This\nmeans that an agent that looks at the outputs of a decoder would remain\noblivious to an attack.","url_abs":"http://arxiv.org/abs/1711.02879v1","url_pdf":"http://arxiv.org/pdf/1711.02879v1.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":"latentpoison-adversarial-attacks-on-the","repo_url":"https://github.com/ToniCreswell/Adversarial-Attack-On-Latent-Space","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.02879","atlas_url":"https://app.syntology.ai/?focus=1711.02879","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}