{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:07:34Z","timestamp":1764842854991,"version":"3.37.3"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s00521-024-09490-8","type":"journal-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T17:02:12Z","timestamp":1708966932000},"page":"7991-8006","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluating robustness of support vector machines with the Lagrangian dual approach"],"prefix":"10.1007","volume":"36","author":[{"given":"Yuting","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0545-3044","authenticated-orcid":false,"given":"Pan","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,26]]},"reference":[{"issue":"18","key":"9490_CR1","doi-asserted-by":"publisher","first-page":"15981","DOI":"10.1007\/s00521-022-07278-2","volume":"34","author":"MS Rais","year":"2022","unstructured":"Rais MS, Zouaidia K, Boudour R (2022) Enhanced decision making in multi-scenarios for autonomous vehicles using alternative bidirectional q network. Neural Comput Appl 34(18):15981\u201315996","journal-title":"Neural Comput Appl"},{"issue":"12","key":"9490_CR2","doi-asserted-by":"publisher","first-page":"9413","DOI":"10.1007\/s00521-021-06369-w","volume":"34","author":"M Cui","year":"2022","unstructured":"Cui M (2022) Big data medical behavior analysis based on machine learning and wireless sensors. Neural Comput Appl 34(12):9413\u20139427","journal-title":"Neural Comput Appl"},{"key":"9490_CR3","doi-asserted-by":"publisher","first-page":"15387","DOI":"10.1007\/s00521-020-04986-5","volume":"34","author":"H Rajadurai","year":"2022","unstructured":"Rajadurai H, Gandhi UD (2022) A stacked ensemble learning model for intrusion detection in wireless network. Neural Comput Appl 34:15387\u201315395","journal-title":"Neural Comput Appl"},{"unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2014) Intriguing properties of neural networks. In: Paper presented at the 2nd international conference on learning representations, Banff, AB, Canada, April 14\u201316 2014","key":"9490_CR4"},{"unstructured":"Dvijotham K, Stanforth R, Gowal S, Mann TA, Kohli P (2018) A dual approach to scalable verification of deep networks. In: Globerson, A., Silva, R. (eds.) Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, vol. 2, pp. 550\u2013559. AUAI Press, Monterey, CA, USA","key":"9490_CR5"},{"key":"9490_CR6","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.ins.2021.04.033","volume":"571","author":"Y Xiao","year":"2021","unstructured":"Xiao Y, Pun C-M (2021) Improving adversarial attacks on deep neural networks via constricted gradient-based perturbations. Inf Sci 571:104\u2013132","journal-title":"Inf Sci"},{"unstructured":"Kurakin A, Goodfellow I, Bengio S (2019) Adversarial examples in the physical world. In: Paper presented at the 5th international conference on learning representations, Toulon, France, April 24\u201326 2019","key":"9490_CR7"},{"doi-asserted-by":"crossref","unstructured":"Wang X, YangY. Deng Y, He K (2021) Adversarial training with fast gradient projection method against synonym substitution based text attacks. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35, pp. 13997\u201314005. AAAI Press, Virtual, Online","key":"9490_CR8","DOI":"10.1609\/aaai.v35i16.17648"},{"doi-asserted-by":"crossref","unstructured":"Gupta K, Ajanthan T (2022) Improved gradient-based adversarial attacks for quantized networks. Preprint at https:\/\/arxiv.org\/abs\/2003.13511","key":"9490_CR9","DOI":"10.1609\/aaai.v36i6.20637"},{"unstructured":"Wong E, Kolter JZ (2020) Learning perturbation sets for robust machine learning. Preprint at https:\/\/arxiv.org\/abs\/2007.08450","key":"9490_CR10"},{"doi-asserted-by":"crossref","unstructured":"Zhang S, Gao H, Shu C, Cao X, Zhou Y, He J (2022) Black-box Bayesian adversarial attack with transferable priors. Mach Learn. pp 1\u201318","key":"9490_CR11","DOI":"10.1007\/s10994-022-06251-3"},{"issue":"3","key":"9490_CR12","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1002\/int.22349","volume":"36","author":"C Chen","year":"2021","unstructured":"Chen C, Huang T (2021) Camdar-adv: generating adversarial patches on 3d object. Int J Intell Syst 36(3):1441\u20131453","journal-title":"Int J Intell Syst"},{"issue":"12","key":"9490_CR13","doi-asserted-by":"publisher","first-page":"2349","DOI":"10.1007\/s10994-020-05916-1","volume":"109","author":"L Wang","year":"2020","unstructured":"Wang L, Zhang H, Yi J, Hsieh C-J, Jiang Y (2020) Spanning attack: reinforce black-box attacks with unlabeled data. Mach Learn 109(12):2349\u20132368","journal-title":"Mach Learn"},{"doi-asserted-by":"crossref","unstructured":"Andriushchenko M, Croce F, Flammarion N, Hein M (2020) Square attack: a query-efficient black-box adversarial attack via random search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J. (eds.) Computer Vision\u2013ECCV 2020\u201316th European Conference, vol. 12368 LNCS, pp. 484\u2013501. Springer, Glasgow, UK","key":"9490_CR14","DOI":"10.1007\/978-3-030-58592-1_29"},{"doi-asserted-by":"crossref","unstructured":"Kim BC, Yu Y, Ro YM (2021) Robust decision-based black-box adversarial attack via coarse-to-fine random search. In: 2021 IEEE International conference on image processing, pp. 3048\u20133052. IEEE, Anchorage, AK, United states","key":"9490_CR15","DOI":"10.1109\/ICIP42928.2021.9506464"},{"key":"9490_CR16","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TIFS.2022.3156809","volume":"17","author":"X-C Li","year":"2022","unstructured":"Li X-C, Zhang X-Y, Yin F, Liu C-L (2022) Decision-based adversarial attack with frequency Mixup. IEEE Trans Inf Forensics Secur 17:1038\u20131052","journal-title":"IEEE Trans Inf Forensics Secur"},{"doi-asserted-by":"crossref","unstructured":"Chen J, Jordan MI, Wainwright MJ (2020) HopSkipJumpAttack: A query-efficient decision-based attack. In: Paper presented at the 2020 IEEE symposium on security and privacy, San Francisco, CA, USA, May 18\u201321 2020","key":"9490_CR17","DOI":"10.1109\/SP40000.2020.00045"},{"unstructured":"Guo C, Frank JS, Weinberger KQ (2020) Low Frequency Adversarial Perturbation. In: Paper presented at the proceedings of the thirty-fifth conference on uncertainty in artificial intelligence, Tel Aviv, Israel, July 22\u201325 2019","key":"9490_CR18"},{"key":"9490_CR19","first-page":"274","volume-title":"International Conference on Machine Learning","author":"A Athalye","year":"2018","unstructured":"Athalye A, Carlini N, Wagner D (2018) Obfuscated gradients give a false sense of security: circumventing defenses to adversarial examples. In: Dy JG, Krause A (eds) International Conference on Machine Learning, vol 80. PMLR, Stockholm, Sweden, pp 274\u2013283"},{"key":"9490_CR20","first-page":"5025","volume-title":"International conference on machine learning","author":"J Uesato","year":"2018","unstructured":"Uesato J, O\u2019donoghue B, Kohli P, Oord A (2018) Adversarial risk and the dangers of evaluating against weak attacks. In: Dy JG, Krause A (eds) International conference on machine learning, vol 80. Stockholm, Sweden, pp 5025\u20135034"},{"doi-asserted-by":"crossref","unstructured":"Zhu Y, Wang F, Wan W, Zhang M (2021) Attack-guided efficient robustness verification of relu neural networks. In: 2021 international joint conference on neural networks, vol. 2021-July, pp. 1\u20138. IEEE, Virtual, Shenzhen, China","key":"9490_CR21","DOI":"10.1109\/IJCNN52387.2021.9534410"},{"unstructured":"Liao H-C, Cheng C-H, Kneissl M, Knoll A (2022) Robustness verification for attention networks using mixed integer programming. Preprint at https:\/\/arxiv.org\/abs\/2202.03932","key":"9490_CR22"},{"unstructured":"Xue H, Zeng X, Lin W, Yang Z, Peng C, Zeng Z (2022) An rnn-based framework for the milp problem in robustness verification of neural networks. In: Proceedings of the Asian conference on computer vision, Macao, China, pp. 1842\u20131857","key":"9490_CR23"},{"unstructured":"Tsay C, Kronqvist J, Thebelt A, Misener R (2021) Partition-based formulations for mixed-integer optimization of trained relu neural networks. In: Advances in neural information processing systems, vol. 4. Virtual, Online, pp. 3068\u20133080","key":"9490_CR24"},{"unstructured":"Tjeng V, Xiao KY, Tedrake R (2019) Evaluating robustness of neural networks with mixed integer programming. In: Paper presented at the 7th international conference on learning representations, New Orleans, LA, USA","key":"9490_CR25"},{"key":"9490_CR26","first-page":"1782","volume":"33","author":"K Jia","year":"2020","unstructured":"Jia K, Rinard M (2020) Efficient exact verification of binarized neural networks. Adv Neural Inf Process Syst 33:1782\u20131795","journal-title":"Adv Neural Inf Process Syst"},{"doi-asserted-by":"crossref","unstructured":"Henzinger TA, Lechner M, ikelic o (2021) Scalable verification of quantized neural networks. In: Proceedings of the AAAI conference on artificial intelligence, vol. 35. Virtual, Online, pp. 3787\u20133795","key":"9490_CR27","DOI":"10.1609\/aaai.v35i5.16496"},{"unstructured":"Song X, Manino E, Sena L, Alves E, Bessa I, Lujan M, Cordeiro L, et al (2021) QNNVerifier: a tool for verifying neural networks using SMT-based model checking. Preprint at https:\/\/arxiv.org\/abs\/2111.13110","key":"9490_CR28"},{"key":"9490_CR29","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-3-030-25540-4_26","volume-title":"International Conference on Computer Aided Verification","author":"G Katz","year":"2019","unstructured":"Katz G, Huang DA, Ibeling D, Julian K, Lazarus C, Lim R, Shah P, Thakoor S, Wu H, Zelji\u0107 A (2019) The marabou framework for verification and analysis of deep neural networks. In: Dillig I, Tasiran S (eds) International Conference on Computer Aided Verification, vol 11561. Springer, New York City, pp 443\u2013452"},{"doi-asserted-by":"crossref","unstructured":"Amir G, Wu H, Barrett C, Katz G (2021) An smt-based approach for verifying binarized neural networks. In: International conference on tools and algorithms for the construction and analysis of systems, Cham, pp. 203\u2013222","key":"9490_CR30","DOI":"10.1007\/978-3-030-72013-1_11"},{"key":"9490_CR31","first-page":"5283","volume-title":"International Conference on Machine Learning","author":"E Wong","year":"2018","unstructured":"Wong E, Kolter Z (2018) Provable defenses against adversarial examples via the convex outer adversarial polytope. In: Dy JG, Krause A (eds) International Conference on Machine Learning, vol 80. PMLR, Stockholm, pp 5283\u20135292"},{"unstructured":"Raghunathan A, Steinhardt J, Liang P (2018) Certified defenses against adversarial examples. In: Paper presented at the 6th international conference on learning representations, Vancouver, BC, Canada","key":"9490_CR32"},{"doi-asserted-by":"crossref","unstructured":"Gehr T, Mirman M, Drachsler-Cohen D, Tsankov P, Chaudhuri S, Vechev M (2018) Ai2: safety and robustness certification of neural networks with abstract interpretation. In: Paper presented at the 2018 IEEE symposium on security and privacy, San Francisco, California, USA","key":"9490_CR33","DOI":"10.1109\/SP.2018.00058"},{"unstructured":"Liu Y, Peng J, Chen L, Zheng Z (2020) Abstract interpretation based robustness certification for graph convolutional networks. In: ECAI 2020, Santiago de Compostela, Online, Spain, pp. 1309\u20131315","key":"9490_CR34"},{"issue":"POPL","key":"9490_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3290354","volume":"3","author":"G Singh","year":"2019","unstructured":"Singh G, Gehr T, P\u00fcschel M, Vechev M (2019) An abstract domain for certifying neural networks. Proc ACM Program Lang 3(POPL):1\u201330","journal-title":"Proc ACM Program Lang"},{"key":"9490_CR36","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/978-3-030-32304-2_15","volume-title":"International Static Analysis Symposium","author":"J Li","year":"2019","unstructured":"Li J, Liu J, Yang P, Chen L, Huang X, Zhang L (2019) Analyzing deep neural networks with symbolic propagation: towards higher precision and faster verification. In: Chang BE (ed) International Static Analysis Symposium, vol 11822. Springer, Porto, pp 296\u2013319"},{"issue":"OOPSLA","key":"9490_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3428253","volume":"4","author":"C Urban","year":"2020","unstructured":"Urban C, Christakis M, W\u00fcstholz V, Zhang F (2020) Perfectly parallel fairness certification of neural networks. Proc ACM Program Lang 4(OOPSLA):1\u201330","journal-title":"Proc ACM Program Lang"},{"doi-asserted-by":"crossref","unstructured":"Ruan W, Huang X, Kwiatkowska M (2018) Reachability analysis of deep neural networks with provable guarantees. In: Lang J (ed) Proceedings of the twenty-seventh international joint conference on artificial intelligence, vol. 2018-July. ijcai.org, Stockholm, Sweden, pp. 2651\u20132659","key":"9490_CR38","DOI":"10.24963\/ijcai.2018\/368"},{"key":"9490_CR39","first-page":"5273","volume-title":"International Conference on Machine Learning","author":"L Weng","year":"2018","unstructured":"Weng L, Zhang H, Chen H, Song Z, Hsieh C-J, Daniel L, Boning D, Dhillon I (2018) Towards fast computation of certified robustness for RELU networks. In: Dy JG, Krause A (eds) International Conference on Machine Learning, vol 80. PMLR, Stockholm, pp 5273\u20135282"},{"unstructured":"Latorre F, Rolland P, Cevher V (2020) Lipschitz constant estimation of neural networks via sparse polynomial optimization. In: Paper presented at the 8th international conference on learning representations, Addis Ababa, Ethiopia","key":"9490_CR40"},{"key":"9490_CR41","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.neucom.2019.10.118","volume":"408","author":"J Cervantes","year":"2020","unstructured":"Cervantes J, Garcia-Lamont F, Rodr\u00edguez-Mazahua L, Lopez A (2020) A comprehensive survey on support vector machine classification: applications, challenges and trends. Neurocomputing 408:189\u2013215. https:\/\/doi.org\/10.1016\/j.neucom.2019.10.118","journal-title":"Neurocomputing"},{"key":"9490_CR42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02300-7_4","volume-title":"Security evaluation of support vector machines in adversarial environments","author":"B Biggio","year":"2014","unstructured":"Biggio B, Corona I, Nelson B, Rubinstein BIP, Maiorca D, Fumera G, Giacinto G, Roli F (2014) Security evaluation of support vector machines in adversarial environments. Springer, Cham"},{"key":"9490_CR43","first-page":"387","volume-title":"Machine learning and knowledge discovery in databases - european conference","author":"B Biggio","year":"2013","unstructured":"Biggio B, Corona I, Maiorca D, Nelson B, \u0160rndi\u0107 N, Laskov P, Giacinto G, Roli F (2013) Evasion attacks against machine learning at test time. In: Blockeel H, Kersting K, Nijssen S, Zelezn\u00fd F (eds) Machine learning and knowledge discovery in databases - european conference, vol 8190. Springer, Prague, pp 387\u2013402"},{"issue":"3","key":"9490_CR44","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1109\/TCYB.2015.2415032","volume":"46","author":"F Zhang","year":"2016","unstructured":"Zhang F, Chan PP, Biggio B, Yeung DS, Roli F (2016) Adversarial feature selection against evasion attacks. IEEE T Cybern 46(3):766\u2013777","journal-title":"IEEE T Cybern"},{"key":"9490_CR45","doi-asserted-by":"publisher","first-page":"2566","DOI":"10.1109\/TIFS.2021.3058771","volume":"16","author":"S Weerasinghe","year":"2021","unstructured":"Weerasinghe S, Alpcan T, Erfani SM, Leckie C (2021) Defending support vector machines against data poisoning attacks. IEEE Trans Inf Forensics Secur 16:2566\u20132578","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"9490_CR46","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-030-32304-2_14","volume-title":"International static analysis symposium","author":"F Ranzato","year":"2019","unstructured":"Ranzato F, Zanella M (2019) Robustness verification of support vector machines. In: Chang BE (ed) International static analysis symposium, vol 11822. Springer, Porto, pp 271\u2013295"},{"doi-asserted-by":"crossref","unstructured":"Cousot P, Cousot R (1977) Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints. In: Proceedings of the 4th ACM SIGACT-SIGPLAN symposium on principles of programming languages","key":"9490_CR47","DOI":"10.1145\/512950.512973"},{"unstructured":"Ranzato F, Zanella M (2019) SAVer GitHub repository. https:\/\/github.com\/svm-abstract-verifier","key":"9490_CR48"},{"issue":"11","key":"9490_CR49","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. Preprint at http:\/\/arxiv.org\/abs\/1708.07747","key":"9490_CR50"},{"unstructured":"Udell M, Boyd S (2013) Maximizing a sum of sigmoids. Optim Eng 1\u201325","key":"9490_CR51"},{"key":"9490_CR52","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep Learning. MIT press, Cambridge"},{"key":"9490_CR53","doi-asserted-by":"publisher","DOI":"10.21236\/ADA594171","volume-title":"Network flows","author":"RK Ahuja","year":"1988","unstructured":"Ahuja RK, Magnanti TL, Orlin JB (1988) Network flows. Massachusetts Institute of Technology, Operations Research Center"},{"unstructured":"Boyd S, Xiao L, Mutapcic A (2004) Subgradient methods. Lecture notes of EE392o, Stanford University, Autumn Quarter 2004, 2004\u20132005","key":"9490_CR54"},{"unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Paper presented at the 3rd international conference on learning representations, San Diego, USA","key":"9490_CR55"},{"unstructured":"Bunel R, De\u00a0Palma A, Desmaison A, Dvijotham K, Kohli P, Torr P, Kumar MP (2020) Lagrangian decomposition for neural network verification. In: Conference on uncertainty in artificial intelligence, pp. 370\u2013379. PMLR","key":"9490_CR56"},{"issue":"3","key":"9490_CR57","first-page":"395","volume":"5","author":"AY Dubovitskii","year":"1965","unstructured":"Dubovitskii AY, Milyutin AA (1965) Extremum problems in the presence of restrictions. Zh Vychisl Mat Mat Fiz 5(3):395\u2013453","journal-title":"Zh Vychisl Mat Mat Fiz"},{"key":"9490_CR58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-82118-9","volume-title":"Minimization Methods for Non-Differentiable Functions.","author":"NZ Shor","year":"1985","unstructured":"Shor NZ (1985) Minimization methods for non-differentiable functions. Springer, Berlin,  Heidelberg. https:\/\/doi.org\/10.1007\/978-3-642-82118-9"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09490-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-09490-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-09490-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T20:16:35Z","timestamp":1713039395000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-09490-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,26]]},"references-count":58,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["9490"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-09490-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2024,2,26]]},"assertion":[{"value":"11 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}