[{"day":"01","OA_place":"repository","researchdata_availability":"no","oa_version":"Accepted Version","ec_funded":1,"month":"04","volume":5,"date_published":"2026-04-01T00:00:00Z","year":"2026","oa":1,"abstract":[{"text":"Modern AI systems increasingly rely on opaque, highly complex models whose inner workings remain inaccessible even to experts. This opacity creates challenges for trust, accountability, and compliance with\r\nemerging regulatory expectations such as the “right to an explanation”. While traditional explainability methods—feature attributions, counterfactuals, surrogate models—and interpretable model classes provide valuable insights for engineers, they often fall short of delivering the contextual, conversational explanations that\r\nreal users expect. Large Language Models (LLMs) offer a promising new avenue for explanation due to their\r\nability to engage interactively, adapt to user needs, and translate technical outputs into more accessible reasoning. However, their tendencies toward hallucination, conflict avoidance, and oversimplification introduce\r\nserious risks when used as explanatory agents. This paper analyzes these opportunities and limitations, examines verification strategies for ensuring explanation fidelity, and situates LLM-generated explanations within\r\nbroader concerns about public trust. The paper concludes by outlining best practices and future research directions for building robust, verifiable, and human-aligned explanation systems.","lang":"eng"}],"publication_status":"published","main_file_link":[{"url":"https://filipcano.org/files/icaart26llm.pdf","open_access":"1"}],"publisher":"Science and Technology Publications","_id":"22103","doi":"10.5220/0014483200004052","project":[{"grant_number":"101020093","name":"Vigilant Algorithmic Monitoring of Software","call_identifier":"H2020","_id":"62781420-2b32-11ec-9570-8d9b63373d4d"}],"date_created":"2026-06-21T22:03:00Z","author":[{"full_name":"Cano Cordoba, Filip","id":"708cad98-e86a-11ef-8098-bdae2d7c6af1","orcid":"0000-0002-0783-904X","first_name":"Filip","last_name":"Cano Cordoba"}],"intvolume":"         5","type":"conference","corr_author":"1","department":[{"_id":"ToHe"}],"status":"public","keyword":["Explainable AI","Large Language Models","Trust in AI"],"das_tickbox":"0","scopus_import":"1","page":"4689-4696","citation":{"chicago":"Cano Cordoba, Filip. “Explaining Decisions One Conversation at a Time: Opportunities and Risks of LLMs as Explainability Assistants.” In <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>, 5:4689–96. Science and Technology Publications, 2026. <a href=\"https://doi.org/10.5220/0014483200004052\">https://doi.org/10.5220/0014483200004052</a>.","ista":"Cano Cordoba F. 2026. Explaining decisions one conversation at a time: Opportunities and risks of LLMs as explainability assistants. Proceedings of the 18th International Conference on Agents and Artificial Intelligence. ICAART: International Conference on Agents and Artificial Intelligence vol. 5, 4689–4696.","mla":"Cano Cordoba, Filip. “Explaining Decisions One Conversation at a Time: Opportunities and Risks of LLMs as Explainability Assistants.” <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>, vol. 5, Science and Technology Publications, 2026, pp. 4689–96, doi:<a href=\"https://doi.org/10.5220/0014483200004052\">10.5220/0014483200004052</a>.","short":"F. Cano Cordoba, in:, Proceedings of the 18th International Conference on Agents and Artificial Intelligence, Science and Technology Publications, 2026, pp. 4689–4696.","apa":"Cano Cordoba, F. (2026). Explaining decisions one conversation at a time: Opportunities and risks of LLMs as explainability assistants. In <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i> (Vol. 5, pp. 4689–4696). Marbella, Spain: Science and Technology Publications. <a href=\"https://doi.org/10.5220/0014483200004052\">https://doi.org/10.5220/0014483200004052</a>","ama":"Cano Cordoba F. Explaining decisions one conversation at a time: Opportunities and risks of LLMs as explainability assistants. In: <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>. Vol 5. Science and Technology Publications; 2026:4689-4696. doi:<a href=\"https://doi.org/10.5220/0014483200004052\">10.5220/0014483200004052</a>","ieee":"F. Cano Cordoba, “Explaining decisions one conversation at a time: Opportunities and risks of LLMs as explainability assistants,” in <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>, Marbella, Spain, 2026, vol. 5, pp. 4689–4696."},"publication":"Proceedings of the 18th International Conference on Agents and Artificial Intelligence","supplementarymaterial":"no","quality_controlled":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","conference":{"start_date":"2026-03-05","name":"ICAART: International Conference on Agents and Artificial Intelligence","location":"Marbella, Spain","end_date":"2026-03-08"},"language":[{"iso":"eng"}],"OA_type":"green","date_updated":"2026-06-24T08:37:00Z","acknowledgement":"This work has been supported by the European Research Council under Grant No.: ERC-2020-AdG\r\n101020093. LLM–based tools have been used as\r\nwriting assistance to help improve presentation.\r\n","publication_identifier":{"eissn":["2184-433X"],"isbn":["9789897587962"],"issn":["2184-3589"]},"title":"Explaining decisions one conversation at a time: Opportunities and risks of LLMs as explainability assistants","article_processing_charge":"No"},{"external_id":{"arxiv":["2410.22374"]},"oa_version":"Preprint","OA_place":"repository","day":"30","month":"06","arxiv":1,"year":"2026","oa":1,"date_published":"2026-06-30T00:00:00Z","volume":2,"publication_status":"published","abstract":[{"text":"Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an ML model to forget part of the data it was trained on. In this paper, we introduce a novel unlearning approach based on Forgetting Neural Networks (FNNs), a neuroscience-inspired architecture that explicitly encodes forgetting through multiplicative decay factors. While FNNs had previously been studied as a theoretical construct, we provide the first concrete implementation and demonstrate their effectiveness for targeted unlearning. We propose several variants with per-neuron forgetting factors, including rank-based assignments guided by activation levels, and evaluate them on MNIST and Fashion-MNIST benchmarks. Our method systematically removes information associated with forget sets while preserving performance on retained data. Membership inference attacks confirm the effectiveness of FNN-based unlearning in erasing information about the training data from the neural network. These results establish FNNs as a promising foundation for efficient and interpretable unlearning. ","lang":"eng"}],"_id":"22294","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2410.22374","open_access":"1"}],"publisher":"SciTePress","author":[{"full_name":"Hatua, Amartya","last_name":"Hatua","first_name":"Amartya"},{"first_name":"Trung","last_name":"Nguyen","full_name":"Nguyen, Trung"},{"last_name":"Cano Cordoba","first_name":"Filip","orcid":"0000-0002-0783-904X","id":"708cad98-e86a-11ef-8098-bdae2d7c6af1","full_name":"Cano Cordoba, Filip"},{"first_name":"Andrew","last_name":"Sung","full_name":"Sung, Andrew"}],"date_created":"2026-07-13T09:46:46Z","doi":"10.5220/0014326500004052","type":"conference","intvolume":"         2","department":[{"_id":"ToHe"}],"das_tickbox":"1","keyword":["Machine Unlearning","Neuroscience-Inspired Machine Learning","Membership Inference Attacks"],"status":"public","publication":"Proceedings of the 18th International Conference on Agents and Artificial Intelligence","citation":{"ieee":"A. Hatua, T. Nguyen, F. Cano Cordoba, and A. Sung, “Machine unlearning using forgetting neural networks,” in <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>, Marbella, Spain, 2026, vol. 2, pp. 1536–1546.","ama":"Hatua A, Nguyen T, Cano Cordoba F, Sung A. Machine unlearning using forgetting neural networks. In: <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>. Vol 2. SciTePress; 2026:1536-1546. doi:<a href=\"https://doi.org/10.5220/0014326500004052\">10.5220/0014326500004052</a>","apa":"Hatua, A., Nguyen, T., Cano Cordoba, F., &#38; Sung, A. (2026). Machine unlearning using forgetting neural networks. In <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i> (Vol. 2, pp. 1536–1546). Marbella, Spain: SciTePress. <a href=\"https://doi.org/10.5220/0014326500004052\">https://doi.org/10.5220/0014326500004052</a>","ista":"Hatua A, Nguyen T, Cano Cordoba F, Sung A. 2026. Machine unlearning using forgetting neural networks. Proceedings of the 18th International Conference on Agents and Artificial Intelligence. ICAART: International Conference on Agents and Artificial Intelligence vol. 2, 1536–1546.","mla":"Hatua, Amartya, et al. “Machine Unlearning Using Forgetting Neural Networks.” <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>, vol. 2, SciTePress, 2026, pp. 1536–46, doi:<a href=\"https://doi.org/10.5220/0014326500004052\">10.5220/0014326500004052</a>.","chicago":"Hatua, Amartya, Trung Nguyen, Filip Cano Cordoba, and Andrew Sung. “Machine Unlearning Using Forgetting Neural Networks.” In <i>Proceedings of the 18th International Conference on Agents and Artificial Intelligence</i>, 2:1536–46. SciTePress, 2026. <a href=\"https://doi.org/10.5220/0014326500004052\">https://doi.org/10.5220/0014326500004052</a>.","short":"A. Hatua, T. Nguyen, F. Cano Cordoba, A. Sung, in:, Proceedings of the 18th International Conference on Agents and Artificial Intelligence, SciTePress, 2026, pp. 1536–1546."},"page":"1536-1546","scopus_import":"1","conference":{"end_date":"2026-03-08","location":"Marbella, Spain","name":"ICAART: International Conference on Agents and Artificial Intelligence","start_date":"2026-03-05"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","language":[{"iso":"eng"}],"quality_controlled":"1","OA_type":"green","title":"Machine unlearning using forgetting neural networks","publication_identifier":{"eissn":["2184-433X"],"isbn":["9789897587962"]},"date_updated":"2026-07-16T09:02:53Z","article_processing_charge":"No"},{"abstract":[{"lang":"eng","text":"Runtime fairness is not a one-time constraint but a dynamic property evaluated over a sequence of decisions. To ensure fairness at runtime, it is necessary to account for past decisions, information neglected by conventional, static classifiers. Traditional fairness shields enforce runtime fairness abruptly, by intervening deterministically whenever a sequence of decisions violates the target for a running fairness measure. This motivates our main conceptual contribution: energy shields. An energy shield is a novel, lightweight, adaptive controller that monitors a sequence of decisions and intervenes probabilistically to ensure runtime fairness smoothly, by utilizing physics-inspired energy functions to nudge the sequence toward fairness: the more unfair the decisions, the stronger the nudging force becomes. This makes energy shields the first fairness shields to provide both short-term safety and long-term liveness guarantees. Safety ensures that the running fairness measure stays within a running target interval with high probability, and liveness ensures that the limit of the fairness measure lies within the limit target interval. Intuitively, the short-term specifies the tolerated fairness values and the long-term specifies the desired fairness values. We also provide a synthesis procedure for constructing the least intrusive energy shield for a given target specification, and demonstrate its efficiency experimentally. We evaluate our energy shields against existing fairness shields through the lens of short- and long-term fairness."}],"publication_status":"published","file_date_updated":"2026-07-16T09:23:15Z","date_published":"2026-07-01T00:00:00Z","oa":1,"year":"2026","arxiv":1,"has_accepted_license":"1","month":"07","day":"01","OA_place":"publisher","researchdata_availability":"no","oa_version":"Published Version","external_id":{"arxiv":["2605.24926"]},"ec_funded":1,"type":"conference","doi":"10.1145/3805689.3806807","project":[{"grant_number":"101020093","call_identifier":"H2020","name":"Vigilant Algorithmic Monitoring of Software","_id":"62781420-2b32-11ec-9570-8d9b63373d4d"}],"author":[{"last_name":"Cano Cordoba","first_name":"Filip","orcid":"0000-0002-0783-904X","full_name":"Cano Cordoba, Filip","id":"708cad98-e86a-11ef-8098-bdae2d7c6af1"},{"last_name":"Henzinger","first_name":"Thomas A","orcid":"0000-0002-2985-7724","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A"},{"first_name":"Konstantin","last_name":"Kueffner","id":"8121a2d0-dc85-11ea-9058-af578f3b4515","full_name":"Kueffner, Konstantin","orcid":"0000-0001-8974-2542"}],"date_created":"2026-07-14T05:32:45Z","publisher":"Association for Computing Machinery","_id":"22321","file":[{"date_updated":"2026-07-16T09:23:15Z","creator":"dernst","file_name":"2026_ACMFACCT_Cano.pdf","date_created":"2026-07-16T09:23:15Z","content_type":"application/pdf","access_level":"open_access","file_size":3129128,"relation":"main_file","checksum":"21e648ea3b529f0df7545ad4b31b0ef4","success":1,"file_id":"22348"}],"scopus_import":"1","citation":{"ieee":"F. Cano Cordoba, T. A. Henzinger, and K. Kueffner, “Energy shields for fairness,” in <i>Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency</i>, Montreal, Canada, 2026, pp. 4243–4275.","ama":"Cano Cordoba F, Henzinger TA, Kueffner K. Energy shields for fairness. In: <i>Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency</i>. Association for Computing Machinery; 2026:4243-4275. doi:<a href=\"https://doi.org/10.1145/3805689.3806807\">10.1145/3805689.3806807</a>","apa":"Cano Cordoba, F., Henzinger, T. A., &#38; Kueffner, K. (2026). Energy shields for fairness. In <i>Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency</i> (pp. 4243–4275). Montreal, Canada: Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3805689.3806807\">https://doi.org/10.1145/3805689.3806807</a>","short":"F. Cano Cordoba, T.A. Henzinger, K. Kueffner, in:, Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, 2026, pp. 4243–4275.","mla":"Cano Cordoba, Filip, et al. “Energy Shields for Fairness.” <i>Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency</i>, Association for Computing Machinery, 2026, pp. 4243–75, doi:<a href=\"https://doi.org/10.1145/3805689.3806807\">10.1145/3805689.3806807</a>.","ista":"Cano Cordoba F, Henzinger TA, Kueffner K. 2026. Energy shields for fairness. Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency. FAccT: Conference on Fairness, Accountability and Transparency, 4243–4275.","chicago":"Cano Cordoba, Filip, Thomas A Henzinger, and Konstantin Kueffner. “Energy Shields for Fairness.” In <i>Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency</i>, 4243–75. Association for Computing Machinery, 2026. <a href=\"https://doi.org/10.1145/3805689.3806807\">https://doi.org/10.1145/3805689.3806807</a>."},"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png"},"page":"4243 - 4275","publication":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","status":"public","das_tickbox":"0","department":[{"_id":"ToHe"}],"ddc":["000"],"corr_author":"1","article_processing_charge":"Yes","acknowledgement":"This work has been supported by the European Research Council under Grant No.: ERC-2020-AdG 101020093.","date_updated":"2026-07-22T06:15:56Z","title":"Energy shields for fairness","OA_type":"gold","supplementarymaterial":"yes","quality_controlled":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","language":[{"iso":"eng"}],"conference":{"start_date":"2026-06-25","name":"FAccT: Conference on Fairness, Accountability and Transparency","end_date":"2026-06-28","location":"Montreal, Canada"}},{"publisher":"Springer Nature","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2507.20711"}],"_id":"21090","intvolume":"     16087","type":"conference","project":[{"_id":"62781420-2b32-11ec-9570-8d9b63373d4d","name":"Vigilant Algorithmic Monitoring of Software","call_identifier":"H2020","grant_number":"101020093"}],"doi":"10.1007/978-3-032-05435-7_1","author":[{"last_name":"Cano Cordoba","first_name":"Filip","orcid":"0000-0002-0783-904X","id":"708cad98-e86a-11ef-8098-bdae2d7c6af1","full_name":"Cano Cordoba, Filip"},{"orcid":"0000-0002-2985-7724","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A","last_name":"Henzinger","first_name":"Thomas A"},{"orcid":"0000-0001-8974-2542","id":"8121a2d0-dc85-11ea-9058-af578f3b4515","full_name":"Kueffner, Konstantin","last_name":"Kueffner","first_name":"Konstantin"}],"date_created":"2026-01-29T16:01:41Z","month":"09","day":"13","OA_place":"repository","oa_version":"Preprint","ec_funded":1,"external_id":{"arxiv":["2507.20711"]},"abstract":[{"text":"Fairness in AI is traditionally studied as a static property evaluated once, over a fixed dataset. However, real-world AI systems operate sequentially, with outcomes and environments evolving over time. This paper proposes a framework for analysing fairness as a runtime property. Using a minimal yet expressive model based on sequences of coin tosses with possibly evolving biases, we study the problems of monitoring and enforcing fairness expressed in either toss outcomes or coin biases. Since there is no one-size-fits-all solution for either problem, we provide a summary of monitoring and enforcement strategies, parametrised by environment dynamics, prediction horizon, and confidence thresholds. For both problems, we present general results under simple or minimal assumptions. We survey existing solutions for the monitoring problem for Markovian and additive dynamics, and existing solutions for the enforcement problem in static settings with known dynamics.","lang":"eng"}],"publication_status":"published","volume":16087,"date_published":"2025-09-13T00:00:00Z","oa":1,"year":"2025","alternative_title":["LNCS"],"arxiv":1,"OA_type":"green","quality_controlled":"1","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","conference":{"name":"RV: Runtime Verification","end_date":"2025-09-19","location":"Graz, Austria","start_date":"2025-09-15"},"language":[{"iso":"eng"}],"article_processing_charge":"No","acknowledgement":"This work is supported by the European Research Council under Grant No.: ERC-2020-AdG 101020093.","date_updated":"2026-02-16T11:57:00Z","publication_identifier":{"eissn":["1611-3349"],"issn":["0302-9743"],"eisbn":["9783032054357"]},"title":"Algorithmic fairness: A runtime perspective","department":[{"_id":"ToHe"}],"corr_author":"1","citation":{"apa":"Cano Cordoba, F., Henzinger, T. A., &#38; Kueffner, K. (2025). Algorithmic fairness: A runtime perspective. In <i>25th International Conference on Runtime Verification</i> (Vol. 16087, pp. 1–21). Graz, Austria: Springer Nature. <a href=\"https://doi.org/10.1007/978-3-032-05435-7_1\">https://doi.org/10.1007/978-3-032-05435-7_1</a>","ama":"Cano Cordoba F, Henzinger TA, Kueffner K. Algorithmic fairness: A runtime perspective. In: <i>25th International Conference on Runtime Verification</i>. Vol 16087. Springer Nature; 2025:1-21. doi:<a href=\"https://doi.org/10.1007/978-3-032-05435-7_1\">10.1007/978-3-032-05435-7_1</a>","ieee":"F. Cano Cordoba, T. A. Henzinger, and K. Kueffner, “Algorithmic fairness: A runtime perspective,” in <i>25th International Conference on Runtime Verification</i>, Graz, Austria, 2025, vol. 16087, pp. 1–21.","chicago":"Cano Cordoba, Filip, Thomas A Henzinger, and Konstantin Kueffner. “Algorithmic Fairness: A Runtime Perspective.” In <i>25th International Conference on Runtime Verification</i>, 16087:1–21. Springer Nature, 2025. <a href=\"https://doi.org/10.1007/978-3-032-05435-7_1\">https://doi.org/10.1007/978-3-032-05435-7_1</a>.","mla":"Cano Cordoba, Filip, et al. “Algorithmic Fairness: A Runtime Perspective.” <i>25th International Conference on Runtime Verification</i>, vol. 16087, Springer Nature, 2025, pp. 1–21, doi:<a href=\"https://doi.org/10.1007/978-3-032-05435-7_1\">10.1007/978-3-032-05435-7_1</a>.","ista":"Cano Cordoba F, Henzinger TA, Kueffner K. 2025. Algorithmic fairness: A runtime perspective. 25th International Conference on Runtime Verification. RV: Runtime Verification, LNCS, vol. 16087, 1–21.","short":"F. Cano Cordoba, T.A. Henzinger, K. Kueffner, in:, 25th International Conference on Runtime Verification, Springer Nature, 2025, pp. 1–21."},"page":"1-21","publication":"25th International Conference on Runtime Verification","status":"public"},{"OA_type":"green","language":[{"iso":"eng"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","conference":{"location":"Philadelphia, PA, United States","end_date":"2025-03-04","name":"AAAI: Conference on Artificial Intelligence","start_date":"2025-02-25"},"quality_controlled":"1","article_processing_charge":"No","title":"Fairness shields: Safeguarding against biased decision makers","acknowledgement":"This work is partly supported by the European Research Council under Grant No.: ERC-2020-AdG 101020093. It is also partially supported by the State Government of Styria, Austria – Department Zukunftsfonds Steiermark.","date_updated":"2026-02-16T12:24:30Z","publication_identifier":{"issn":["2159-5399"],"eissn":["2374-3468"]},"department":[{"_id":"ToHe"}],"corr_author":"1","issue":"15","citation":{"apa":"Cano Cordoba, F., Henzinger, T. A., Könighofer, B., Kueffner, K., &#38; Mallik, K. (2025). Fairness shields: Safeguarding against biased decision makers. In <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i> (Vol. 39, pp. 15659–15668). Philadelphia, PA, United States: Association for the Advancement of Artificial Intelligence. <a href=\"https://doi.org/10.1609/aaai.v39i15.33719\">https://doi.org/10.1609/aaai.v39i15.33719</a>","ama":"Cano Cordoba F, Henzinger TA, Könighofer B, Kueffner K, Mallik K. Fairness shields: Safeguarding against biased decision makers. In: <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>. Vol 39. Association for the Advancement of Artificial Intelligence; 2025:15659-15668. doi:<a href=\"https://doi.org/10.1609/aaai.v39i15.33719\">10.1609/aaai.v39i15.33719</a>","ieee":"F. Cano Cordoba, T. A. Henzinger, B. Könighofer, K. Kueffner, and K. Mallik, “Fairness shields: Safeguarding against biased decision makers,” in <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>, Philadelphia, PA, United States, 2025, vol. 39, no. 15, pp. 15659–15668.","short":"F. Cano Cordoba, T.A. Henzinger, B. Könighofer, K. Kueffner, K. Mallik, in:, Proceedings of the 39th AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, 2025, pp. 15659–15668.","chicago":"Cano Cordoba, Filip, Thomas A Henzinger, Bettina Könighofer, Konstantin Kueffner, and Kaushik Mallik. “Fairness Shields: Safeguarding against Biased Decision Makers.” In <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>, 39:15659–68. Association for the Advancement of Artificial Intelligence, 2025. <a href=\"https://doi.org/10.1609/aaai.v39i15.33719\">https://doi.org/10.1609/aaai.v39i15.33719</a>.","ista":"Cano Cordoba F, Henzinger TA, Könighofer B, Kueffner K, Mallik K. 2025. Fairness shields: Safeguarding against biased decision makers. Proceedings of the 39th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 39, 15659–15668.","mla":"Cano Cordoba, Filip, et al. “Fairness Shields: Safeguarding against Biased Decision Makers.” <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>, vol. 39, no. 15, Association for the Advancement of Artificial Intelligence, 2025, pp. 15659–68, doi:<a href=\"https://doi.org/10.1609/aaai.v39i15.33719\">10.1609/aaai.v39i15.33719</a>."},"page":"15659-15668","publication":"Proceedings of the 39th AAAI Conference on Artificial Intelligence","scopus_import":"1","status":"public","_id":"19665","publisher":"Association for the Advancement of Artificial Intelligence","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2412.11994","open_access":"1"}],"intvolume":"        39","type":"conference","date_created":"2025-05-11T22:02:39Z","author":[{"first_name":"Filip","last_name":"Cano Cordoba","full_name":"Cano Cordoba, Filip","id":"708cad98-e86a-11ef-8098-bdae2d7c6af1","orcid":"0000-0002-0783-904X"},{"first_name":"Thomas A","last_name":"Henzinger","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A","orcid":"0000-0002-2985-7724"},{"last_name":"Könighofer","first_name":"Bettina","full_name":"Könighofer, Bettina"},{"id":"8121a2d0-dc85-11ea-9058-af578f3b4515","full_name":"Kueffner, Konstantin","orcid":"0000-0001-8974-2542","first_name":"Konstantin","last_name":"Kueffner"},{"full_name":"Mallik, Kaushik","id":"0834ff3c-6d72-11ec-94e0-b5b0a4fb8598","orcid":"0000-0001-9864-7475","first_name":"Kaushik","last_name":"Mallik"}],"project":[{"_id":"62781420-2b32-11ec-9570-8d9b63373d4d","call_identifier":"H2020","name":"Vigilant Algorithmic Monitoring of Software","grant_number":"101020093"}],"doi":"10.1609/aaai.v39i15.33719","month":"04","oa_version":"Preprint","external_id":{"arxiv":["2412.11994"]},"ec_funded":1,"day":"11","OA_place":"repository","abstract":[{"lang":"eng","text":"As AI-based decision-makers increasingly influence human lives, it is a growing concern that their decisions may be unfair or biased with respect to people's protected attributes, such as gender and race. Most existing bias prevention measures provide probabilistic fairness guarantees in the long run, and it is possible that the decisions are biased on any decision sequence of fixed length. We introduce *fairness shielding*, where a symbolic decision-maker---the fairness shield---continuously monitors the sequence of decisions of another deployed black-box decision-maker, and makes interventions so that a given fairness criterion is met while the total intervention costs are minimized. We present four different algorithms for computing fairness shields, among which one guarantees fairness over fixed horizons, and three guarantee fairness periodically after fixed intervals. Given a distribution over future decisions and their intervention costs, our algorithms solve different instances of bounded-horizon optimal control problems with different levels of computational costs and optimality guarantees. Our empirical evaluation demonstrates the effectiveness of these shields in ensuring fairness while maintaining cost efficiency across various scenarios."}],"publication_status":"published","arxiv":1,"date_published":"2025-04-11T00:00:00Z","volume":39,"oa":1,"year":"2025"}]