{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T21:20:22Z","timestamp":1792185622621,"version":"4.4.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T00:00:00Z","timestamp":1621814400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>Circuit obfuscation is a recently proposed defense mechanism to protect the intellectual property (IP) of digital integrated circuits (ICs) from reverse engineering. There have been effective schemes, such as satisfiability (SAT)-checking based attacks that can potentially decrypt obfuscated circuits, which is called deobfuscation. Deobfuscation runtime could be days or years, depending on the layouts of the obfuscated ICs. Hence, accurately pre-estimating the deobfuscation runtime within a reasonable amount of time is crucial for IC designers to optimize their defense. However, it is challenging due to (1) the complexity of graph-structured circuit; (2) the varying-size topology of obfuscated circuits; (3) requirement on efficiency for deobfuscation method. This study proposes a framework that predicts the deobfuscation runtime based on graph deep learning techniques to address the challenges mentioned above. A conjunctive normal form (CNF) bipartite graph is utilized to characterize the complexity of this SAT problem by analyzing the SAT attack method. Multi-order information of the graph matrix is designed to identify the essential features and reduce the computational cost. To overcome the difficulty in capturing the dynamic size of the CNF graph, an energy-based kernel is proposed to aggregate dynamic features into an identical vector space. Then, we designed a framework, Deep Survival Analysis with Graph (DSAG), which integrates energy-based layers and predicts runtime inspired by censored regression in survival analysis. Integrating uncensored data with censored data, the proposed model improves the standard regression significantly. DSAG is an end-to-end framework that can automatically extract the determinant features for deobfuscation runtime. Extensive experiments on benchmarks demonstrate its effectiveness and efficiency.<\/jats:p>","DOI":"10.3389\/fdata.2021.608286","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T02:31:28Z","timestamp":1621823488000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep Graph Learning for Circuit Deobfuscation"],"prefix":"10.3389","volume":"4","author":[{"given":"Zhiqian","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaurav","family":"Kolhe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadi Mardani","family":"Kamali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Setareh","family":"Rafatirad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai Manoj","family":"Pudukotai Dinakarrao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houman","family":"Homayoun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Tien","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,5,24]]},"reference":[{"key":"B1","first-page":"410","article-title":"The community structure of SAT formulas,","volume-title":"Theory and Applications of Satisfiability Testing\u2013SAT 2012. SAT 2012. Lecture Notes in Computer Science","author":"Ans\u00f3tegui","year":"2012"},{"key":"B2","first-page":"11","article-title":"On the modularity of industrial SAT instances,","author":"Ans\u00f3tegui","year":"2011","journal-title":"CCIA"},{"key":"B3","article-title":"Diffusion-convolutional neural networks,","volume-title":"NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Atwood","year":"2016"},{"key":"B4","doi-asserted-by":"publisher","first-page":"97","DOI":"10.13154\/tches.v2019.i1.97-122","article-title":"SMT Attack: next generation attack on obfuscated circuits with capabilities and performance beyond the SAT attacks","volume":"2019","author":"Azar","year":"2018","journal-title":"IACR Trans. Cryptogr. Hardw. Embedded Syst"},{"key":"B5","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"B6","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric deep learning: going beyond euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Process. Mag"},{"key":"B7","first-page":"151","article-title":"The complexity of theorem-proving procedures,","volume-title":"Proceedings of the Third Annual ACM Symposium on Theory of Computing","author":"Cook","year":"1971"},{"key":"B8","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering,","volume-title":"NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Defferrard","year":"2016"},{"key":"B9","article-title":"Satisfiability as a classification problem,","volume-title":"Irish Conference on Artificial Intelligence and Cognitive Science","author":"Devlin","year":"2008"},{"key":"B10","doi-asserted-by":"crossref","DOI":"10.14722\/ndss.2015.23218","article-title":"Integrated circuit (IC) decamouflaging: reverse engineering camouflaged ICS within minutes,","volume-title":"NDSS Symposium 2015","author":"El Massad","year":"2015"},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-94144-8_17","article-title":"Sharpness of the satisfiability threshold for non-uniform random k-SAT,","volume-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence Best Sister Conferences","author":"Friedrich","year":"2018"},{"key":"B12","article-title":"A modularity-based random sat instances generator,","volume-title":"IJCAI'15: Proceedings of the 24th International Conference on Artificial Intelligence","author":"Gir\u00e1ldez-Cru","year":"2015"},{"key":"B13","article-title":"Inductive representation learning on large graphs,","volume-title":"NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Hamilton","year":""},{"key":"B14","article-title":"Representation learning on graphs: methods and applications","author":"Hamilton","year":"","journal-title":"arXiv"},{"key":"B15","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.acha.2010.04.005","article-title":"Wavelets on graphs via spectral graph theory","volume":"30","author":"Hammond","year":"2011","journal-title":"Appl. Comput. Harm. Anal"},{"key":"B16","first-page":"237","article-title":"Complexity of k-SAT,","volume-title":"Proceedings. Fourteenth Annual IEEE Conference on Computational Complexity","author":"Impagliazzo","year":"1999"},{"key":"B17","year":"2012","journal-title":"IHS Technology Press Release: Top 5 Most Counterfeited Parts Represent a"},{"key":"B18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ISVLSI.2018.00080","article-title":"Lut-lock: a novel lut-based logic obfuscation for fpga-bitstream and asic-hardware protection,","volume-title":"IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","author":"Kamali","year":"2018"},{"key":"B19","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/978-1-4684-2001-2_9","article-title":"Reducibility among combinatorial problems,","volume-title":"Complexity of Computer Computations","author":"Karp","year":"1972"},{"key":"B20","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1109\/ISVLSI.2018.00066","article-title":"Hardware obfuscation using strong pufs,","volume-title":"2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","author":"Khaleghi","year":"2018"},{"key":"B21","article-title":"Semi-supervised classification with graph convolutional networks,","volume-title":"ICLR","author":"Kipf","year":"2017"},{"key":"B22","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1137\/1.9781611974348.86","article-title":"Regularized parametric regression for high-dimensional survival analysis,","volume-title":"Proceedings of the 2016 SIAM International Conference on Data Mining","author":"Li","year":"2016"},{"key":"B23","first-page":"433","article-title":"Oracle-guided incremental sat solving to reverse engineer camouflaged logic circuits,","volume-title":"Design, Automation & Test in Europe Conference & Exhibition (DATE), 2016","author":"Liu","year":"2016"},{"key":"B24","first-page":"1280","article-title":"Deep learning for algorithm portfolios,","volume-title":"AAAI'16: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","author":"Loreggia","year":"2016"},{"key":"B25","first-page":"141","article-title":"On the hardness of SAT with community structure,","volume-title":"Theory and Applications of Satisfiability Testing\u2013SAT 2016. SAT 2016. Lecture Notes in Computer Science","author":"Mull","year":"2016"},{"key":"B26","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines,","volume-title":"ICML'10: Proceedings of the 27th International Conference on International Conference on Machine Learning","author":"Nair","year":"2010"},{"key":"B27","first-page":"252","article-title":"Impact of community structure on SAT solver performance,","volume-title":"Theory and Applications of Satisfiability Testing\u2013SAT 2014. SAT 2014. Lecture Notes in Computer Science","author":"Newsham","year":"2014"},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1145\/3194554.3194596","article-title":"Srclock: SAT-resistant cyclic logic locking for protecting the hardware,","volume-title":"Proceedings of the 2018 on Great Lakes Symposium on VLSI, GLSVLSI '18","author":"Roshanisefat","year":"2018"},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/HST.2017.7951805","article-title":"APPSAT: Approximately deobfuscating integrated circuits,","volume-title":"2017 IEEE International Symposium on Hardware Oriented Security and Trust (HOST)","author":"Shamsi","year":"2017"},{"key":"B30","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/MSP.2012.2235192","article-title":"The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains","volume":"30","author":"Shuman","year":"2013","journal-title":"IEEE Signal Process. Mag"},{"key":"B31","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1109\/HST.2015.7140252","article-title":"Evaluating the security of logic encryption algorithms,","volume-title":"2015 IEEE International Symposium on Hardware Oriented Security and Trust (HOST)","author":"Subramanyan","year":"2015"},{"key":"B32","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3214306","article-title":"Machine learning for survival analysis: a survey","volume":"51","author":"Wang","year":"2019","journal-title":"ACM Comput. Surv"},{"key":"B34","article-title":"A comprehensive survey on graph neural networks","author":"Wu","year":"2019","journal-title":"arXiv"},{"key":"B35","first-page":"1","article-title":"Delay locking: security enhancement of logic locking against IC counterfeiting and overproduction,","volume-title":"ACM\/EDAC\/IEEE Design Automation Conference (DAC)","author":"Xie","year":"2017"},{"key":"B36","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TCAD.2018.2801220","article-title":"Anti-SAT: mitigating sat attack on logic locking","volume":"38","author":"Xie","year":"2018","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst"},{"key":"B37","doi-asserted-by":"crossref","DOI":"10.1109\/HST.2016.7495588","article-title":"Sarlock: SAT attack resistant logic locking,","volume-title":"2016 IEEE International Symposium on Hardware Oriented Security and Trust (HOST)","author":"Yasin","year":""},{"key":"B38","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1109\/TCAD.2015.2511144","article-title":"On improving the security of logic locking","volume":"35","author":"Yasin","year":"","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst"},{"key":"B39","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1145\/3133956.3133985","article-title":"Provably-secure logic locking: from theory to practice,","volume-title":"Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security","author":"Yasin","year":"2017"},{"key":"B40","article-title":"Deep learning on graphs: a survey","author":"Zhang","year":"2018","journal-title":"arXiv"},{"key":"B41","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/ICCAD.2017.8203759","article-title":"CycSAT: SAT-based attack on cyclic logic encryptions,","volume-title":"2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)","author":"Zhou","year":"2017"},{"key":"B42","article-title":"Graph neural networks: a review of methods and applications","author":"Zhou","year":"2018","journal-title":"arXiv"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2021.608286\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T02:32:04Z","timestamp":1621823524000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2021.608286\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,24]]},"references-count":42,"alternative-id":["10.3389\/fdata.2021.608286"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2021.608286","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,24]]},"article-number":"608286"}}