{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:01:09Z","timestamp":1780761669995,"version":"3.54.1"},"reference-count":29,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Science"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jocs.2026.102884","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:30:05Z","timestamp":1778085005000},"page":"102884","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Towards robust language models: XAI-Driven generation and mitigation of targeted adversarial examples under restricted knowledge"],"prefix":"10.1016","volume":"98","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7749-4251","authenticated-orcid":false,"given":"Tomasz","family":"Walkowiak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0620-8123","authenticated-orcid":false,"given":"Mateusz","family":"Gniewkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Klonowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pawe\u0142","family":"Walkowiak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jocs.2026.102884_b1","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.jocs.2026.102884_b2","series-title":"Computational Science \u2013 ICCS 2025","first-page":"49","article-title":"Precise language deception: XAI driven targeted adversarial examples with restricted knowledge","author":"Gniewkowski","year":"2025"},{"key":"10.1016\/j.jocs.2026.102884_b3","series-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"10.1016\/j.jocs.2026.102884_b4","series-title":"Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part III","first-page":"387","article-title":"Evasion attacks against machine learning at test time","volume":"8190","author":"Biggio","year":"2013"},{"key":"10.1016\/j.jocs.2026.102884_b5","series-title":"A complete list of all (arxiv) adversarial example papers","author":"Carlini","year":"2019"},{"key":"10.1016\/j.jocs.2026.102884_b6","series-title":"Adversarial examples for evaluating reading comprehension systems","author":"Jia","year":"2017"},{"key":"10.1016\/j.jocs.2026.102884_b7","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8018","article-title":"Is BERT really robust? A strong baseline for natural language attack on text classification and entailment","volume":"vol. 34","author":"Jin","year":"2020"},{"key":"10.1016\/j.jocs.2026.102884_b8","series-title":"43rd IEEE Symposium on Security and Privacy, SP 2022, San Francisco, CA, USA, May 22-26, 2022","first-page":"1987","article-title":"Bad characters: Imperceptible NLP attacks","author":"Boucher","year":"2022"},{"key":"10.1016\/j.jocs.2026.102884_b9","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1162\/tacl_a_00279","article-title":"Trick me if you can: Human-in-the-loop generation of adversarial question answering examples","volume":"7","author":"Wallace","year":"2019","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.jocs.2026.102884_b10","series-title":"Global challenge for safe and secure LLMs track 1","author":"Jia","year":"2024"},{"key":"10.1016\/j.jocs.2026.102884_b11","series-title":"Despite \u201csuper-human\u201d performance, current LLMs are unsuited for decisions about ethics and safety","author":"Albrecht","year":"2022"},{"key":"10.1016\/j.jocs.2026.102884_b12","series-title":"Proceedings on \u201cI Can\u2019T Believe It\u2019s Not Better: Failure Modes in the Age of Foundation Models\u201d At NeurIPS 2023 Workshops","first-page":"103","article-title":"Adversarial attacks and defenses in large language models: Old and new threats","volume":"vol. 239","author":"Schwinn","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b13","series-title":"2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19\u201324, 2020","first-page":"1","article-title":"When explainability meets adversarial learning: Detecting adversarial examples using SHAP signatures","author":"Fidel","year":"2020"},{"issue":"10","key":"10.1016\/j.jocs.2026.102884_b14","doi-asserted-by":"crossref","first-page":"4381","DOI":"10.1109\/TIV.2023.3296227","article-title":"Robust adversarial attacks detection based on explainable deep reinforcement learning for UAV guidance and planning","volume":"8","author":"Hickling","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.jocs.2026.102884_b15","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102884_b16","series-title":"Texture- and shape-based adversarial attacks for vehicle detection in synthetic overhead imagery","author":"Yeghiazaryan","year":"2024"},{"key":"10.1016\/j.jocs.2026.102884_b17","series-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13\u201317, 2016","first-page":"1135","article-title":"\u201dWhy should I trust you?\u201d: Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"10.1016\/j.jocs.2026.102884_b18","series-title":"Are your explanations reliable? Investigating the stability of LIME in explaining text classifiers by marrying XAI and adversarial attack","author":"Burger","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b19","series-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, la, USA, December 10\u201316, 2023","article-title":"Jailbroken: How does LLM safety training fail?","author":"Wei","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b20","series-title":"Universal and transferable adversarial attacks on aligned language models","author":"Zou","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b21","series-title":"Autodan: Interpretable gradient-based adversarial attacks on large language models","author":"Zhu","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b22","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28\u2013December 9, 2022","article-title":"Exploring the limits of domain-adaptive training for detoxifying large-scale language models","author":"Wang","year":"2022"},{"key":"10.1016\/j.jocs.2026.102884_b23","series-title":"44th IEEE Symposium on Security and Privacy, SP 2023, San Francisco, CA, USA, May 21\u201325, 2023","first-page":"346","article-title":"Analyzing leakage of personally identifiable information in language models","author":"Lukas","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b24","series-title":"ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30\u2013October 4, 2023, Krak\u00d3w, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023)","first-page":"875","article-title":"Do not trust me: Explainability against text classification","volume":"vol. 372","author":"Gniewkowski","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b25","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.jocs.2026.102884_b26","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","article-title":"Sentence-BERT: Sentence embeddings using siamese BERT-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.jocs.2026.102884_b27","series-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics","first-page":"2970","article-title":"Learning to ignore adversarial attacks","author":"Zhang","year":"2023"},{"key":"10.1016\/j.jocs.2026.102884_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2021.103457","article-title":"GLocalX - From local to global explanations of black box AI models","volume":"294","author":"Setzu","year":"2021","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.jocs.2026.102884_b29","series-title":"Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022","first-page":"322","article-title":"GALE: Globally assessing local explanations","volume":"vol. 196","author":"Xenopoulos","year":"2022"}],"container-title":["Journal of Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S187775032600102X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S187775032600102X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:41:52Z","timestamp":1780760512000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S187775032600102X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":29,"alternative-id":["S187775032600102X"],"URL":"https:\/\/doi.org\/10.1016\/j.jocs.2026.102884","relation":{},"ISSN":["1877-7503"],"issn-type":[{"value":"1877-7503","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards robust language models: XAI-Driven generation and mitigation of targeted adversarial examples under restricted knowledge","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jocs.2026.102884","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102884"}}