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 201–300 of 336
Robust and Adversarial Data Mining
Wang, F. (2015) · The Sydney eScholarship Repository (The University of Sydney) · Cited by 4
Privacy Games: Optimal Protection Mechanism Design for Bayesian and Differential Privacy.Preprint
Shokri, R. (2014) · arXiv (Cornell University) · Cited by 4
Resilient Linear Classification: An Approach to Deal with Attacks on Training DataPreprint
Park, S., Weimer, J. E., & Lee, I. (2017) · ScholarlyCommons (University of Pennsylvania) · doi:10.48550/arxiv.1708.03366 · Cited by 4
“, [9, 17, 19]) usually assumes a known aacker behavior and/or goal – which is likely unknown in complex CPS applications.”
A Grid Based Adversarial Clustering AlgorithmPreprint
Wei, W., Gupta, N., & Xi, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.04780 · Cited by 4
“In [9, 21], Stackelberg game is used to model the sequential actions between a defender/classifier and active adversaries.”
Adaptive Learning in Two-Player Stackelberg Games with Application to Network SecurityPreprint
Yang, G., Poovendran, R., & Hespanha, J. P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03253 · Cited by 4
“Existing results on learning in Stackelberg games are limited to linear or quadratic costs and finite action sets [21]–[23], which are too restrictive for many applications including network security.”
BackgroundThe Limits of Optimal Pricing in the DarkPreprint
Dawkins, Q., Han, M., & Xu, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.01707 · Cited by 4
“Most works in this space has focused on classification [11, 20, 43, 17, 25, 21, 12], regression problems [31, 15, 13] and distinguishing distributions [40, 41].”
BackgroundStrategic Classification with Randomised ClassifiersPreprint
Geary, J., & Gouk, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.01313 · Cited by 4
“However, earlier works such as Dalvi et al. [2004] and Brückner and Scheffer [2011] show that efforts to address the problem predate this.”
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?Preprint
Shao, H., Xie, S., & Yang, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.01936 · Cited by 4
“The research on strategic machine learning—which focuses on designing machine learning algorithms that remain robust in the presence of strategic behaviors—dates back to the works of Dalvi et al. [2004], Br¨uckner and Scheffer [2011], Dekel et al. [2010].”
Sharma, D., & Sun, A. (2025) · neural information processing systems · doi:10.52202/085713-3393 · Cited by 3
Inherent Tradeoffs in the Fair Determination of Risk Scores
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603206 · Cited by 3
The Adaptive Arms Race: Redefining Robustness in AI Security
Tsingenopoulos, I., Rimmer, V., Preuveneers, D., Pierazzi, F., Cavallaro, L., & Joosen, W. (2025) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1109/raid67961.2025.00015 · Cited by 3
“(1) [44].”
Bilateral Cognitive Security Games in Networked Control Systems under Stealthy Injection Attacks
Nguyen, A. T., Zhu, Q., & Teixeira, A. M. H. (2025) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc57313.2025.11312998 · Cited by 3
The Game-Theoretic Symbiosis of Trust and AI in Networked Systems
Ge, Y., & Zhu, Q. (2025) · Advances in information security · doi:10.1007/978-3-031-93867-2_3 · Cited by 3
Adversarial Forecasting Through Adversarial Risk Analysis Within a DDDAS Framework
Ekin, T., Naveiro, R., & Camacho, J. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-52670-1_29 · Cited by 3
Adversarial Deep Learning with Stackelberg Games
Chivukula, A. S., Yang, X., & Liu, W. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-36808-1_1 · Cited by 3
Provably accurate and scalable linear classifiers in hyperbolic spaces
Pan, C., Chien, E., Tabaghi, P., Peng, J., & Milenković, O. (2023) · Knowledge and Information Systems · doi:10.1007/s10115-022-01820-3 · Cited by 3
“Strategic classification deals with the problem of learning a classier when the learner relies on data that is provided by strategic agents in an online manner [23], [24].”
BackgroundNext Generation Trustworthy Fraud Detection
Xie, S., & Yu, P. S. (2018) · IEEE International Conference on Collaboration and Internet Computing (CIC) · doi:10.1109/cic.2018.00045 · Cited by 3
“To deal with this in-competence, proactive detectors have been proposed [8], [28], [33], [34], [43], [7], [28], [41], [6].”
MethodMaMa: A Game-Theoretic Approach for Designing Safe Agentic SystemsPreprint
Nöther, J., Singla, A., & Radanovic, G. (2026) · arXiv.org · doi:10.48550/arxiv.2602.04431 · Cited by 3
“To the best of our knowledge, this is the first work to apply this framework to the design of agentic systems which remain safe under agent failure.”
A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation
Cao, Q., Zeng, S., & Zhang, J. (2025) · neural information processing systems · doi:10.52202/085713-0778 · Cited by 2
“We consider the PBO model for spam classification tasks, as proposed by [16]: where w denotes the classifier parameters, ( x, y ) represents vectorized training data, l (resp. l ′ ) corresponds to the classifier (resp. adversarial generator) loss, Reg ( · ) denotes the regularization term, and φ (…”
InfluentialOptimal Strategies Against Generative Attacks
Mor, R., Peterfreund, E., Gavish, M., & Globerson, A. (2020) · International Conference on Learning Representations · Cited by 2
Scalable Optimal Classifiers for Adversarial Settings Under Uncertainty
Roussillon, B., & Loiseau, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-90370-1_5 · Cited by 2
Modeling by topological data analysis and game theory for analyzing data poisoning phenomena
Феррара, М. (2025) · AIMS Mathematics · doi:10.3934/math.2025693 · Cited by 2
Automated Attacks on Compression-Based Classifiers
Burago, I., & Lowd, D. (2015) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/2808769.2808778 · Cited by 2
“Robust learning algorithms can reduce the vulnerability of linear classifiers, so that attackers need to make larger modifications in order to evade detection [9,10,15,35].”
BackgroundAlgorithmic Monoculture and Social Welfare
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603211 · Cited by 2
Sun, H., Wang, Y., Yang, H., Huo, K., & Li, Y. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3389611 · Cited by 2
“The Stackelberg game is commonly used to model the interactions between the learner and the data provider as a two-player nonzero-sum sequential game, as introduced in [30].”
MethodTowards a Game-Theoretic Understanding of Explanation-Based Membership Inference Attacks
Kumari, K., Jadliwala, M. S., Jha, S. K., & Maiti, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-74835-6_13 · Cited by 3
ARTIFICIAL INTELLIGENCE WITH SAFE AND SECURE DEEP LEARNING ARCHITECTURES
Shah, H. (2019) · INTERNATIONAL RESEARCH JOURNAL OF ENGINEERING AND APPLIED SCIENCES · doi:10.55083/irjeas.2019.v07i03010 · Cited by 2
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603198 · Cited by 2
Chen, L. (2019) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.3844 · Cited by 2
“, well-crafted attack as it shows most effective) by comparisons with other popular defense methods, including (1) feature evenness (denoted as Defense1 ) which enables the Original-Classifier to learn more evenly-distributed feature weights using the method proposed in [78]; (2) classifier retraining (denoted as Defe…”
MethodWhich Echo Chamber? Regions of Attraction in Learning with Decision-Dependent Distributions.Preprint
Dong, R., & Ratliff, L. J. (2021) · arXiv (Cornell University) · Cited by 2
Do You Think You Can Hold Me? The Real Challenge of Problem-Space Evasion AttacksPreprint
Berger, H., Dvir, A. Z., Hajaj, C., & Ronen, R. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.04293 · Cited by 2
“Additional approaches to design robust classifiers are the use of a non-zero-sum game [46, 47, 55–57], or a Stackelberg game, where the learner is the leader, while the attacker is the follower [47, 56, 57, 104].”
MethodMistake, Manipulation and Margin Guarantees in Online Strategic ClassificationPreprint
Shen, L., Ho-Nguyen, N., Giang-Tran, K.-H., & Kılınç-Karzan, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.18176 · Cited by 2
PAC Learning with ImprovementsPreprint
Attias, I., Blum, A. L., Naggita, K., Saless, D., Sharma, D., & Walter, M. R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.03184 · Cited by 2
“Early research framed this problem as a Stackelberg competition [HMPW16, BS11], where negatively classified agents manipulate their features to obtain more favorable outcomes if the benefits outweigh the costs.”
An Adaptive Algorithm for Bilevel Optimization on Riemannian ManifoldsPreprint
Shi, X., Xiao, R., & Jiang, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.06042 · Cited by 2
“In this section, we introduce the tangent-space conjugate gradient method [81, 10], which is used in Section 3.1.”
InfluentialBhargava, R. (2019) · Purdue e-Pubs (Purdue University System) · doi:10.25394/pgs.9034142 · Cited by 2
Prediction games machine learning in the presence of an adversary
Brückner, M. (2012) · Cited by 2
Self-citationBilevel learningPreprint
Grazzi, R., Pontil, M., Salzo, S., & Zemkoho, A. B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.01621 · Cited by 2
“For more details on this subject, interested readers are referred to [19, 39, 137].”
Reeves, A., & Ashenden, D. (2025) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2025.130 · Cited by 1
The Illusion of Optimal Defense: Static Interdiction Under Adaptive and Persistent Attackers
Shin, J., Zhai, S., Carley, L. R., & Carley, K. M. (2026) · Proceedings of the AAAI Symposium Series · doi:10.1609/aaaiss.v9i1.42948 · Cited by 1
“Second, we plan to develop an environment where adaptive attackers and defenders interact in real time to find optimal solutions using game-theoretic approaches such as Stackelberg games (Br¨uckner and Scheffer 2011).”
Deceitful Attacks in Security Games.
Nguyen, T. H., Wellman, M. P., & Sinha, A. (2018) · National Conference on Artificial Intelligence · Cited by 1
Discovering Imperfectly Observable Adversarial Actions using Anomaly Detection
Petrova, O., Durkota, K., Alperovich, G., Horak, K., Najman, M., Bošanský, B., & Lisý, V. (2020) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/mjeo7917 · Cited by 1
Improving crowd labeling using Stackelberg models
Yang, W., & Li, C. (2021) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-021-01276-x · Cited by 1
“1 3 training a classifier), so it is widely used in adversary learning [3, 18, 42].”
BackgroundThe Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603204 · Cited by 1
Mitigating Bias in Algorithmic Decision-making: Evaluating Claims and Practices
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603212 · Cited by 1
Design and implementation of robust systems for secure malware detection
Maiorca, D. (2016) · VEprints - Universita degli Studi di Cagliari · Cited by 1
Robust Large Margin Approaches for Machine Learning in Adversarial Settings
Torkamani, M. A. (2016) · Scholars' Bank (University of Oregon) · Cited by 1
Alabdulmohsin, I. (2017) · King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology) · doi:10.25781/kaust-hc4jh · Cited by 1
“Several lines of research have used such a game-theoretic setting [133, 134, 79, 135].”
MethodK-Beam Subgradient Descent for Minimax Optimization.Preprint
Hamm, J., & Noh, Y. (2018) · arXiv (Cornell University) · Cited by 1
Using Randomness to Improve Robustness of Machine-Learning Models Against Evasion AttacksPreprint
Yang, F., & Chen, Z. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03601 · Cited by 1
“Several other works [8, 9, 27, 34] model the adversarial learning problem as a Stackelberg game.”
BackgroundWahab, O. A. (2017) · Spectrum Research Repository (Concordia University) · Cited by 1
Incentivizing Truthfulness Through Audits in Strategic ClassificationPreprint
Estornell, A., Das, S., & Vorobeychik, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.09147 · Cited by 1
“…Evans 2016), or on designing classifiers that are robust in the sense that the prediction remains unchanged even after budget-constrained feature modifications (Brückner and Scheffer 2011, 2012; Hardt et al. 2016; Li and Vorobeychik 2018; Madry et al. 2018; Tong et al. 2019; Wong and Kolter 2018).”
BackgroundArgumentation Models for Cyber AttributionPreprint
Nunes, E., Shakarian, P., Simari, G. I., & Ruef, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.02171 · Cited by 2
“research that looks at modeling the interaction between the learner (adversary) and the classifier in terms of a competition using Stackelberg games [4], [3].”
BackgroundSequential Strategic ScreeningPreprint
Cohen, L., Sharifi-Malvajerdi, S., Stangl, K., Vakilian, A., & Ziani, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.13397 · Cited by 1
“As Br¨uckner & Scheffer (2011) observe, this is a bi-level optimization problem and is NP-hard (Jeroslow, 1985) to compute, even when constraints and objectives are linear.”
BackgroundDiscovering Optimal Scoring Mechanisms in Causal Strategic PredictionPreprint
Yan, T., Gupta, S., & Lipton, Z. C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.06804 · Cited by 1
The Adaptive Arms Race: Redefining Robustness in AI SecurityPreprint
Tsingenopoulos, I., Rimmer, V., Preuveneers, D., Pierazzi, F., Cavallaro, L., & Joosen, W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.13435 · Cited by 1
“(1) [44].”
Econometric Estimation and Data-Driven Credit Market FailuresPreprint
Gamba, A., & Hennessy, C. A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4852424 · Cited by 1
The Active and Noise-Tolerant Strategic PerceptronPreprint
Balcan, M.-F., & Beyhaghi, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.01783 · Cited by 1
“Strategic classification, on the other hand, is an emerging area of modern machine learning research that models scenarios where input features are provided by individuals who might manipulate them to receive better outcomes [BS11, HMPW16].”
LIPIcs, Volume 256, FORC 2023, Complete Volume
Talwar, K. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.forc.2023 · Cited by 1
Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?Preprint
Ahmadi, S., Blum, A. L., Xu, H., & Yao, F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.20061 · Cited by 1
“Our work is related to the growing line of research on strategic ML that studies learning from data provided by strategic agents [Dalvi et al., 2004, Dekel et al., 2008, Brückner and Scheffer, 2011].”
LIPIcs, Volume 218, FORC 2022, Complete Volume
Celis, L. E. (2022) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.forc.2022 · Cited by 1
Accounting for real world phenomena in machine learning and mechanism design
Bishop, N. (2023) · ePrints Soton (University of Southampton) · Cited by 1
On the impact of randomization on robustness in machine learning
Pinot, R. (2020) · theses.fr (ABES) · doi:10.70675/0c663121zbccez4affza78az8028a3491269 · Cited by 1
Low-Complexity Algorithm for Stackelberg Prediction Games with Global OptimalityPreprint
Wei, T., Xu, Y., Wang, X., Ho, P., R., B. S. M., State, R., & Ottersten, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.02676 · Cited by 1
“The setting can be cast as a Stackelberg prediction game (Brückner & Scheffer, 2011; Bishop et al., 2020), in which a learner and a strategic data provider interact sequentially.”
A Theoretical Game of Attacks via Compositional SkillsPreprint
Wu, X., Zhang, H., Umrawal, A. K., & Varshney, L. R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.01034 · Cited by 1
“Early work in classical ML formalized adversarial classification as strategic interactions between learners and manipulators, including Stackelberg games where the learner commits and the adversary best-responds (Dalvi et al., 2004; Brückner & Scheffer, 2011).”
Retraining Seeks Stable SignalsPreprint
Hardt, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.15623 · Cited by 1
“More recently, special cases of performative prediction appeared in computer science in areas such as strategic classification (Brückner and Scheffer, 2011 ; Hardt et al., 2016 ), algorithmic fairness (Ensign et al., 2018 ; Hashimoto et al., 2018 ; Liu et al., 2018 ), and concept/distribution shift…”
Online Learning in Stackelberg Security Games with Time-Varying Attack IntensitiesPreprint
Chen, G., Zhang, S., Wang, Y., & Ji, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.01703 · Cited by 1
“In the Stackelberg Security Game formulation (Conitzer & Sandholm, 2006; Brückner & Scheffer, 2011; Li & Sethi, 2017; Castiglioni et al., 2020), a leader (defender) first commits to a randomized patrolling or protection strategy, and a follower (attacker) observes and best responds to the leader’s…”
Rational Multiparty Computation
Wallrabenstein, J. R. (2014) · Purdue e-Pubs (Purdue University System) · Cited by 1
Algorithmic monoculture and social welfare
(2023) · The Societal Impacts of Algorithmic Decision-Making · doi:10.1145/3603195.3603202
Designing Vaccines that Are Robust to Virus Escape
Panda, S., & Vorobeychik, Y. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9710
“This formulation can be viewed as a Stackelberg game (Paruchuri et al. 2008) (Brückner and Scheffer 2011) between the designer and the virus in which the virus minimizes the cost of escaping the antibody chosen by the designer.”
BackgroundWater Decision-Making Under Uncertainty
Odame, A. (2015) · Digital Commons - USU (Utah State University) · doi:10.26076/c520-4fc8
Herne teoretická optimalizace detekce škodlivého chování
Raman, S. (2016) · Cvut DSpace (Czech Technical University)
Combining game theory and statistical learning for security, privacy and network systems
Loiseau, P. (2016) · Graduate School and Research Center in Digital Science (EURECOM)
Effective detection of security compromises in enterprises using feature engineering
Duan, J. (2016) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)
Reasoning about Cyber Threat Actors
Nunes, E. (2018)
Designing Evaluation Rules That Are Robust to Strategic Behavior
Kleinberg, J. M., & Raghavan, M. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i09.7118
“…(Dalvi et al. 2004); recent formulations have considered a broader range of settings in which an evaluator publishes a rule and an agent then manipulates their features (Hardt et al. 2016; Br¨uckner and Scheffer 2011; Dong et al. 2018; Milli et al. 2019; Hu, Immorlica, and Vaughan 2019).”
BackgroundXu, H., & Nguyen, T. H. (2020) · Springer eBooks · doi:10.1007/978-3-030-55692-1_3
Extracting and Harnessing Interpretation in Data Mining
Liu, N. (2021) · OakTrust (Texas A&M University Libraries)
Social Aspects of Algorithms: Fairness, Diversity, and Resilience to Strategic Behavior
Ahmadi, S. (2021) · University Libraries (University of Maryland) · doi:10.13016/by4d-qcv1
Rande, N. (2021) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2021.36539
Minimax Detection (MAD) for Computer Security: A Dynamic Program Characterization
Sayin, M. O., Sahabandu, D., Zaman, M. A. U., Poovendran, R., & Başar, T. (2021) · Wiley eBooks · doi:10.1002/9781119723950.ch7
Using Machine Learning in Adversarial Environments
Sandia National Labs., A., Davis, W., IV, Administration, U. A. S. F. H. R. A., Dunlavy, D., Nauer, K., Letter, M., Butler, K., Murchison, N., Forsythe, C., & Vorobeychik, Y. (2016) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/1563076
Metric-Fair Classifier DerandomizationPreprint
Wu, J. M., Chen, Y., & Liu, Y. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.07826
“Cost functions studied in the strategic classification literature include the L2 (Hardt et al., 2016; Brückner & Scheffer, 2011) and Mahalanobis (Chen et al., 2021) distances, both of which are metrics with known LSH families (Andoni & Indyk, 2006; Jain et al., 2008).”
BackgroundSocially Responsible Machine Learning: On the Preservation of Individual Privacy and Fairness
Zhang, X. (2021) · Deep Blue (University of Michigan) · doi:10.7302/3005
Strategic Interactions and Incentive Mechanisms on Multi-scale Networks
Jin, K. (2023) · Deep Blue (University of Michigan) · doi:10.7302/7360
Screening with Disadvantaged Agents
Beyhaghi, H., Camara, M. K., Hartline, J. D., Johnsen, A., & Long, S. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.forc.2023.6
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603213
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603205
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603196
How Do Classifiers Induce Agents to Behave Strategically?
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603201
How Do Classifiers Induce Agents to Behave Strategically?
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603210
Raghavan, M. (2023) · ACM eBooks · doi:10.1145/3603195.3603214
An Adversarial Learning with Sum of Top-K Loss Framework for Credit Card Fraud Detection
Yan, Y., Xiang, Q., Li, Z., Xia, Y., Zhu, B., & Jiang, R. (2023) · International Conference on Intelligent Human-Machine Systems and Cybernetics · doi:10.1109/ihmsc58761.2023.00057
“We compared the performance of our proposed AST framework with three kinds of baselines: Logistic regression, the SOTA TabNet [4] and the adversarial learning model (SPG-Linear) in [12].”
MethodResultNCGAN: A Calibrated Oversampling Technique for Fraud Detection
Yan, Y., Xia, Y., Xiang, Q., Zhu, B., Li, Z., & Jiang, R. (2023) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca59871.2023.10392583
“Another strands of research focus on the tackling the adversarial attacks towards machine learning models [2], [3], [4].”
BackgroundLeveraging Noisy Observations in Zero-Sum Games
Athanasakos, E. M., & Perlaza, S. M. (2024) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itw61385.2024.10806983
Accelerated Fully First-Order Methods for Bilevel and Minimax OptimizationPreprint
Li, C. J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.00914
Analysis of Two Game Theory Models: Cournot Model and Stackelberg Model
Gao, J. (2024) · Highlights in Science Engineering and Technology · doi:10.54097/b43vxw93
“In such a setup, both players can increase their outcomes by utilizing a minimax strategy [8].”
BackgroundThe multi-class Stackelberg prediction game with least squares loss
Han, S., Lin, Y., Wang, J., & Zhang, L. (2024) · Optimization and Engineering · doi:10.1007/s11081-024-09921-4
“When general cost functions are utilized for the learner and the data generator, the resulting models are generally non-convex optimization problems and are NP-hard (Brückner and Scheffer 2011, Section 3.1).”
InfluentialFairness, Accuracy, and Unreliable DataPreprint
Stangl, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.16040
Exploring Score-Based Ranking Fairness in Marketplace Environments Through Simulation
Silva, L. C., & Lucrédio, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-79035-5_19
Ahmadi, S., Beyhaghi, H., Blum, A. L., & Naggita, K. (2025) · Digital Signal Processing and Artificial Intelligence for Automatic Learning · doi:10.6025/dspaial/2025/4/1/24-41
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.