{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:33:30Z","timestamp":1776886410454,"version":"3.51.2"},"reference-count":0,"publisher":"EasyChair","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Deep neural networks (DNNs) are revolutionizing the way complex systems are de- signed, developed and maintained. As part of the life cycle of DNN-based systems, there is often a need to modify a DNN in subtle ways that affect certain aspects of its behav- ior, while leaving other aspects of its behavior unchanged (e.g., if a bug is discovered and needs to be fixed, without altering other functionality). Unfortunately, retraining a DNN is often difficult and expensive, and may produce a new DNN that is quite different from the original. We leverage recent advances in DNN verification and propose a technique for modifying a DNN according to certain requirements, in a way that is provably minimal, does not require any retraining, and is thus less likely to affect other aspects of the DNN\u2019s behavior. Using a proof-of-concept implementation, we demonstrate the usefulness and potential of our approach in addressing two real-world needs: (i) measuring the resilience of DNN watermarking schemes; and (ii) bug repair in already-trained DNNs.<\/jats:p>","DOI":"10.29007\/699q","type":"proceedings-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T22:10:11Z","timestamp":1590617411000},"page":"260-240","source":"Crossref","is-referenced-by-count":22,"title":["Minimal Modifications of Deep Neural Networks using Verification"],"prefix":"10.29007","volume":"73","author":[{"given":"Ben","family":"Goldberger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guy","family":"Katz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph","family":"Keshet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11545","event":{"name":"LPAR23. LPAR-23: 23rd International Conference on Logic for Programming, Artificial Intelligence and Reasoning"},"container-title":["EPiC Series in Computing"],"original-title":[],"deposited":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T22:10:20Z","timestamp":1590617420000},"score":1,"resource":{"primary":{"URL":"https:\/\/easychair.org\/publications\/paper\/CWhF"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":0,"URL":"https:\/\/doi.org\/10.29007\/699q","relation":{},"ISSN":["2398-7340"],"issn-type":[{"value":"2398-7340","type":"print"}],"subject":[]}}