{"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/specification-guided-safety-verification-for","title":"Specification-Guided Safety Verification for Feedforward Neural Networks","arxiv_id":"1812.06161","date":"2018-12-14","proceeding":null,"authors":["Weiming Xiang","Hoang-Dung Tran","Taylor T. Johnson"],"abstract":"This paper presents a specification-guided safety verification method for\nfeedforward neural networks with general activation functions. As such\nfeedforward networks are memoryless, they can be abstractly represented as\nmathematical functions, and the reachability analysis of the neural network\namounts to interval analysis problems. In the framework of interval analysis, a\ncomputationally efficient formula which can quickly compute the output interval\nsets of a neural network is developed. Then, a specification-guided\nreachability algorithm is developed. Specifically, the bisection process in the\nverification algorithm is completely guided by a given safety specification.\nDue to the employment of the safety specification, unnecessary computations are\navoided and thus the computational cost can be reduced significantly.\nExperiments show that the proposed method enjoys much more efficiency in safety\nverification with significantly less computational cost.","url_abs":"http://arxiv.org/abs/1812.06161v1","url_pdf":"http://arxiv.org/pdf/1812.06161v1.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":"specification-guided-safety-verification-for","repo_url":"https://github.com/transafeailab/nnv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"specification-guided-safety-verification-for","repo_url":"https://github.com/verivital/nnv","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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}