Martin Pawelczyk

43 papers A* 10A 3Journal 26Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks. CoRR Samira Abedini, Sina Mavali, Lea Schönherr, Martin Pawelczyk, Rebekka Burkholz
2026	J	`jnl`	Easy Data Unlearning Bench. CoRR Roy Rinberg, Pol Puigdemont, Martin Pawelczyk, Volkan Cevher
2025	J	`jnl`	Efficiently Verifiable Proofs of Data Attribution. CoRR Ari Karchmer, Martin Pawelczyk, Seth Neel
2025	J	`jnl`	Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models. CoRR Martin Pawelczyk, Lillian Sun, Zhenting Qi, Aounon Kumar, Himabindu Lakkaraju
2025	A*	`conf`	Machine Unlearning Fails to Remove Data Poisoning Attacks. ICLR Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu, Gautam Kamath, Ayush Sekhari, Seth Neel
2025	J	`jnl`	Train Once, Answer All: Many Pretraining Experiments for the Cost of One. CoRR Sebastian Bordt, Martin Pawelczyk
2024	J	`jnl`	Deep Neural Networks and Tabular Data: A Survey. IEEE Trans. Neural Networks Learn. Syst. Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, Gjergji Kasneci
2024	J	`jnl`	Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference. CoRR Catherine Huang, Martin Pawelczyk, Himabindu Lakkaraju
2024	A*	`conf`	I Prefer Not to Say: Protecting User Consent in Models with Optional Personal Data. AAAI Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle, Gjergji Kasneci
2024	A*	`conf`	In-Context Unlearning: Language Models as Few-Shot Unlearners. ICML Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju
2024	J	`jnl`	Machine Unlearning Fails to Remove Data Poisoning Attacks. CoRR Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu, Gautam Kamath, Ayush Sekhari, Seth Neel
2024	—	`—`	On the Generation of Realistic and Robust Counterfactual Explanations for Algorithmic Recourse Martin Pawelczyk
2024	J	`jnl`	Towards Non-Adversarial Algorithmic Recourse. CoRR Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj, Gjergji Kasneci
2024	—	`conf`	Towards Non-adversarial Algorithmic Recourse. xAI (3) Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj, Gjergji Kasneci
2023	A*	`conf`	Gaussian Membership Inference Privacy. NeurIPS Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
2023	J	`jnl`	Gaussian Membership Inference Privacy. CoRR Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
2023	J	`jnl`	In-Context Unlearning: Language Models as Few Shot Unlearners. CoRR Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju
2023	A*	`conf`	Language Models are Realistic Tabular Data Generators. ICLR Vadim Borisov, Kathrin Seßler, Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
2023	A	`conf`	On the Privacy Risks of Algorithmic Recourse. AISTATS Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel
2023	A*	`conf`	On the Trade-Off between Actionable Explanations and the Right to be Forgotten. ICLR Martin Pawelczyk, Tobias Leemann, Asia Biega, Gjergji Kasneci
2023	A*	`conf`	Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse. ICLR Martin Pawelczyk, Teresa Datta, Johannes van den Heuvel, Gjergji Kasneci, Himabindu Lakkaraju
2022	J	`jnl`	Algorithmic Recourse in the Face of Noisy Human Responses. CoRR Martin Pawelczyk, Teresa Datta, Johannes van den Heuvel, Gjergji Kasneci, Himabindu Lakkaraju
2022	J	`jnl`	Decomposing Counterfactual Explanations for Consequential Decision Making. CoRR Martin Pawelczyk, Lea Tiyavorabun, Gjergji Kasneci
2022	A	`conf`	Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis. AISTATS Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi, Sohini Upadhyay, Himabindu Lakkaraju
2022	J	`jnl`	I Prefer not to Say: Operationalizing Fair and User-guided Data Minimization. CoRR Tobias Leemann, Martin Pawelczyk, Christian Thomas Eberle, Gjergji Kasneci
2022	J	`jnl`	Language Models are Realistic Tabular Data Generators. CoRR Vadim Borisov, Kathrin Seßler, Tobias Leemann, Martin Pawelczyk, Gjergji Kasneci
2022	J	`jnl`	On the Privacy Risks of Algorithmic Recourse. CoRR Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel
2022	J	`jnl`	On the Trade-Off between Actionable Explanations and the Right to be Forgotten. CoRR Martin Pawelczyk, Tobias Leemann, Asia Biega, Gjergji Kasneci
2022	A*	`conf`	OpenXAI: Towards a Transparent Evaluation of Model Explanations. NeurIPS Chirag Agarwal, Satyapriya Krishna, Eshika Saxena, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju
2022	J	`jnl`	OpenXAI: Towards a Transparent Evaluation of Model Explanations. CoRR Chirag Agarwal, Eshika Saxena, Satyapriya Krishna, Martin Pawelczyk, Nari Johnson, Isha Puri, Marinka Zitnik, Himabindu Lakkaraju
2022	J	`jnl`	Rethinking Stability for Attribution-based Explanations. CoRR Chirag Agarwal, Nari Johnson, Martin Pawelczyk, Satyapriya Krishna, Eshika Saxena, Marinka Zitnik, Himabindu Lakkaraju
2021	—	`conf`	CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms. NeurIPS Datasets and Benchmarks Martin Pawelczyk, Sascha Bielawski, Johannes van den Heuvel, Tobias Richter, Gjergji Kasneci
2021	J	`jnl`	CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms. CoRR Martin Pawelczyk, Sascha Bielawski, Johannes van den Heuvel, Tobias Richter, Gjergji Kasneci
2021	J	`jnl`	Deep Neural Networks and Tabular Data: A Survey. CoRR Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, Gjergji Kasneci
2021	J	`jnl`	Gaussian Experts Selection using Graphical Models. CoRR Hamed Jalali, Martin Pawelczyk, Gjergji Kasneci
2021	—	`conf`	Model Selection in Local Approximation Gaussian Processes: A Markov Random Fields Approach. IEEE BigData Hamed Jalali, Martin Pawelczyk, Gjergji Kasneci
2021	J	`jnl`	On the Connections between Counterfactual Explanations and Adversarial Examples. CoRR Martin Pawelczyk, Shalmali Joshi, Chirag Agarwal, Sohini Upadhyay, Himabindu Lakkaraju
2020	A*	`conf`	Learning Model-Agnostic Counterfactual Explanations for Tabular Data. WWW Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
2020	A*	`conf`	Leveraging Model Inherent Variable Importance for Stable Online Feature Selection. KDD Johannes Haug, Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
2020	J	`jnl`	Leveraging Model Inherent Variable Importance for Stable Online Feature Selection. CoRR Johannes Haug, Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
2020	A	`conf`	On Counterfactual Explanations under Predictive Multiplicity. UAI Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
2020	J	`jnl`	On Counterfactual Explanations under Predictive Multiplicity. CoRR Martin Pawelczyk, Klaus Broelemann, Gjergji Kasneci
2019	J	`jnl`	Towards User Empowerment. CoRR Martin Pawelczyk, Johannes Haug, Klaus Broelemann, Gjergji Kasneci