Stackelberg games for adversarial prediction problems
The DOI matches its Crossref record; 18 of the 19 references it cites were found in a registry or an index.
Abstract
The standard assumption of identically distributed training and test data is violated when test data are generated in response to a predictive model. This becomes apparent, for example, in the context of email spam filtering, where an email service provider employs a spam filter and the spam sender can take this filter into account when generating new emails. We model the interaction between learner and data generator as a Stackelberg competition in which the learner plays the role of the leader and the data generator may react on the leader's move. We derive an optimization problem to determine the solution of this game and present several instances of the Stackelberg prediction game. We show that the Stackelberg prediction game generalizes existing prediction models. Finally, we explore properties of the discussed models empirically in the context of email spam filtering.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Evasion attacks can be protected against by devising systems composed of multiple classifiers, as outlined in [137], or other adversary-aware learning algorithms (e.g.one-and-a-halfclass multiple classifiers) as outlined in [135].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [137]
Citations
Cites
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
Wächter, A., & Biegler, L. T. (2006) · Mathematical Programming · doi:10.1007/s10107-004-0559-y · Cited by 9,483 · cited 1×
“To solve the nonlinear program of the SPG with logistic loss we use the Ipopt solver [16].”
MethodAdvances in Neural Information Processing Systems 20
Bonilla, E. V., Chai, K. M. A., & Williams, C. K. I. (2008) · neural information processing systems · Cited by 2,846
A Generalized Representer Theorem
Schölkopf, B., Herbrich, R., & Smola, A. J. (2001) · Lecture Notes in Computer Science · doi:10.1007/3-540-44581-1_27 · Cited by 1,589 · cited 1×
“Making use of the representer theorem [13], we can now express weight vector w as a linear combination of the mapped training instances; that is,”
MethodDataset Shift in Machine Learning
(2008) · doi:10.7551/mitpress/9780262170055.001.0001 · Cited by 1,553
An overview of bilevel optimization
Colson, B., Marcotte, P., & Savard, G. (2007) · Annals of Operations Research · doi:10.1007/s10479-007-0176-2 · Cited by 1,409 · cited 1×
“Numerous approaches that address bilevel programs have been studied, for instance, based on gradient descent, penalty function, and trust-region methods; see, for instance, [2] for a detailed survey.”
BackgroundThe polynomial hierarchy and a simple model for competitive analysis
Jeroslow, R. G. (1985) · Mathematical Programming · doi:10.1007/bf01586088 · Cited by 425 · cited 2×
“Even the simplest instance in which all constraints and objectives are linear is known to be NP-hard [8].”
BackgroundNightmare at test time: robust learning by feature deletion
Globerson, A., & Roweis, S. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143889 · Cited by 309 · cited 1×
“Similarly, worstcase solutions to classification games in which the adversary deletes input features or performs arbitrary feature transformation have been studied [3, 6, 7, 14, 4].”
Background(2000) · Applied Physics Letters · doi:10.1162/153244303321897726 · Cited by 157
Learning to classify with missing and corrupted features
Dekel, O., Shamir, O., & Xiao, L. (2009) · Machine Learning · doi:10.1007/s10994-009-5124-8 · Cited by 139 · cited 1×
“Similarly, worstcase solutions to classification games in which the adversary deletes input features or performs arbitrary feature transformation have been studied [3, 6, 7, 14, 4].”
Background
Cited by
Items 301–336 of 336
Strategic classification for non-uniform preferences using penalty labels and randomisation
Singh, M. K., & Kulkarni, A. A. (2025) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-025-09725-5
Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It
Kim, D., Choi, H., Rasool, M. J. A., & Oh, G. (2025) · Transactions on machine learning research · doi:10.48550/arxiv.2509.02391
“…Stackelberg interactions, and performative prediction analyze how agents respond to public classifiers and how repeated retraining interacts with distributional shifts (Hardt et al., 2016a; Brückner & Scheffer, 2011; Perdomo et al., 2020; Mendler-Dünner et al., 2020; Miller et al., 2020).”
Computing Strategic Responses to Non-Linear ClassifiersPreprint
Geary, J., Gao, B., & Gouk, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.21560
“The Strategic Classification [9, 2] literature examines the setting where a Learner is attempting to classify a population of Agents in that can independently perturb their representations in response to the learned classifier.”
A Dual Learning Model for Last-Mile Delivery PricingPreprint
Bhattacharya, M. (2025) · Research Square · doi:10.21203/rs.3.rs-8231891/v1
The Externalities of Exploration and How Data Diversity Helps Exploitation
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603199
Dagstuhl Manifestos, Volume 3, Issue 1, January - December 2013, Complete Issue
Informatik, S. D. L.-Z. F. (2014) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/dagman.3.1
Selection Problems in the Presence of Implicit Bias
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603200
Learning and Socially Responsible Decision-Making with Strategic Feedback
Chen, Y. (2024) · eScholarship (California Digital Library)
Reasoning about Cyber Threat Actors
(2018) · Arizona State University Library Digital Repository (Arizona State University)
Adversarial games in machine learning : challenges and applications
Berard, H. (2022) · Papyrus : Institutional Repository (Université de Montréal) · doi:10.71781/9796
Adaptieve aanvallen en verdedigingen voor robuuste en veilige AI-systemen
Tsingenopoulos, I. (2024) · Lirias
Strategic and counterfactual reasoning in AI-assisted decision making
Tsirtsis, S. (2025) · Publication Server of Kaiserslautern University of Technology (Kaiserslautern University of Technology) · doi:10.26204/kluedo/9284
Structuring Incentives in the Development and Use of Artificial Intelligence
Shavit, Y. G. (2024) · Digital Access to Scholarship at Harvard (DASH) (Harvard University)
The Adaptive Arms Race: Redefining Robustness in AI Security
Tsingenopoulos, I., Rimmer, V., Preuveneers, D., Pierazzi, F., Cavallaro, L., & Joosen, W. (2025) · UCL Discovery (University College London)
On Randomized Algorithms in Online Strategic ClassificationPreprint
Hutton, C., Melrod, A., & Shao, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.06257
“Strategic classification lies at the intersection of machine learning and game theory and studies learning problems in which self-interested agents strategically modify their observable features to obtain favorable predictions (Br¨uckner and Scheffer, 2011; Hardt et al., 2016).”
Exploiting GANs Against IDSs: A Systematic Review, Meta-Analysis, and Case Study Evaluation
Alslman, Y., Alkasassbeh, M. S., & Abdel‐Rahman, M. J. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3677234
“Moreover, using game-theoretic models is not new in the field of generating adversarial samples; Brückner et al. [92] used a Stackelberg game to generate spam emails.”
Uncertainty quantification in data-centric machine learning
Rodemann, J. M. (2026) · Electronic Theses of LMU Munich (Ludwig-Maximilians-Universität München) · doi:10.5282/edoc.36738
Learning in the Presence of Strategic Data Sources : Models and Solutions
Roussillon, B. (2021) · theses.fr (ABES) · doi:10.70675/34f54589z0465z4a11z868bzf78ba278d0ca
Advances in Optimal Transport : Low-Rank Structures and Applications in Machine Learning
Scetbon, M. (2023) · theses.fr (ABES) · doi:10.70675/47c63da2zae73z4885z97e6z036715c1c184
Adversarial attacks : a theoretical journey
Meunier, L. (2022) · theses.fr (ABES) · doi:10.70675/c792c77cz8c7bz4930za4fbz79b40c3d10d1
Stochastic Graphical Bilinear Bandits
Rizk, G. (2022) · theses.fr (ABES) · doi:10.70675/637a167czbdfbz4644z8ddazdedcfcc1eca0
Privacy, Prediction, and AllocationPreprint
Jacobsen, B., & Kohli, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.15596
“In other words, ULA has less to gain than ILA from additional tools for making such inferences.”
Yu, J., Li, Y., Wang, Y., & Chen, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461930
Prediction-Intervention Games and Invariant SetsPreprint
Kühne, L., Schur, F., & Peters, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.16828
“Our work relates to strategic classification [4, 19], its causal extensions [35, 51], formulations with asymmetric leader/follower objectives [12], and performative prediction [39].”
No-regret optimization of time-varying bilevel problemsPreprint
Mauduit, E., Berthier, É., & Simonetto, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.20962
“This formulation is closely related to Stackelberg games [Brückner and Scheffer, 2011].”
Privacy, Prediction, and Allocation
Jacobsen, B., & Kohli, N. (2026) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.forc.2026.20
Blázquez, L. C. (2025) · Hispania-revista Espanola De Historia · doi:10.3989/hispania.2025.1350
Non-Linear Strategic Classification Made PracticalPreprint
Geary, J., Gao, B., & Gouk, H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.28204
“Building off of the setting established by [2, 14], Strategic Classification was originally formulated by Hardt et al. [15].”
EPMD: A Framework for LLM-Enhanced Ad Auctions
Wang, B., Zhang, B., Gong, J., Yu, C., & Qi, Q. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818144
Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing ObjectivesPreprint
Naggita, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.05710
Single-Loop Gradient Algorithms for Pessimistic Bilevel Optimization ProblemsPreprint
Cao, Q., Zeng, B., Zeng, S., & Zhang, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.11183
“Specifically, we consider the following feature-map generalization of the spam classification model in [13]: Here, w denotes the classifier parameters, while x and y denote the vectorized messages and their associated labels, respectively.”
Channel-Calibrated Aggregate Monitoring for Coordinated Manipulation
Zhang, R. (2026) · Library, Museums and Press - UDSpace (University of Delaware)
Dang, L., Alfatemi, A., Xiong, K., Aledhari, M., Chehri, A., Al-Maliki, S., & Rahouti, M. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3742225
Wu, X., Farooq, J., & Li, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-40367-4_27
Multi-Strategy Adversarial Continual Learning for Dynamic Financial Graphs
Hughes, O., & Brennan, C. (2026) · International Journal of Data Sciences and Intelligent Systems
Metadata
- Authors
- Brückner, M., & Scheffer, T.
- Affiliations
- University of Potsdam (DE)
- ORCID
- Scheffer, Tobias
- Venue
- Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
- Publisher
- ACM
- Published
- 2011-08-21
- Pages
- 547-555
- OpenAlex
- W1966912382
- Cited by
- 229
- References
- 19
- Citations by year
- 2026: 6 · 2025: 9 · 2024: 11 · 2023: 32 · 2022: 9 · 2021: 29 · 2020: 25 · 2019: 16 · 2018: 28 · 2017: 16 · 2016: 21 · 2015: 7 · 2014: 8 · 2013: 6 · 2012: 6
- FWCI
- 4.80
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Funders
- Deutsche Forschungsgemeinschaft
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Social Sciences › Decision Sciences › Management Science and Operations Research › Game Theory and Applications
- Keywords
- Stackelberg game, email spam detection, game-theoretic optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.