A Machine Learning Framework for Off Ball Defensive Role and Performance Evaluation in Football
- URL: http://arxiv.org/abs/2601.00748v1
- Date: Fri, 02 Jan 2026 17:10:36 GMT
- Title: A Machine Learning Framework for Off Ball Defensive Role and Performance Evaluation in Football
- Authors: Sean Groom, Shuo Wang, Francisco Belo, Axl Rice, Liam Anderson,
- Abstract summary: We introduce a co-dependent Hidden Markov Model (CDHMM) tailored to corner kicks in football games.<n>Our model infers time-resolved man-marking and zonal assignments directly from player tracking data.<n>We propose a novel framework for defensive credit attribution and a role-conditioned ghosting method for counterfactual analysis of off-ball defensive performance.
- Score: 3.418921713486739
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Evaluating off-ball defensive performance in football is challenging, as traditional metrics do not capture the nuanced coordinated movements that limit opponent action selection and success probabilities. Although widely used possession value models excel at appraising on-ball actions, their application to defense remains limited. Existing counterfactual methods, such as ghosting models, help extend these analyses but often rely on simulating "average" behavior that lacks tactical context. To address this, we introduce a covariate-dependent Hidden Markov Model (CDHMM) tailored to corner kicks, a highly structured aspect of football games. Our label-free model infers time-resolved man-marking and zonal assignments directly from player tracking data. We leverage these assignments to propose a novel framework for defensive credit attribution and a role-conditioned ghosting method for counterfactual analysis of off-ball defensive performance. We show how these contributions provide a interpretable evaluation of defensive contributions against context-aware baselines.
Related papers
- Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attacks [3.206339985805037]
Dashed Line Defense (DLD) is a plug-and-play post-processing method specifically designed to withstand adaptive query strategies.<n>By introducing ambiguity in how the observed loss reflects the true adversarial strength of candidate examples, DLD prevents attackers from reliably analyzing and adapting their queries.<n>We provide theoretical guarantees of DLD's defense capability and validate its effectiveness through experiments on ImageNet.
arXiv Detail & Related papers (2026-02-09T14:02:32Z) - Better Prevent than Tackle: Valuing Defense in Soccer Based on Graph Neural Networks [22.27208191198993]
DEFCON (DEFensive CONtribution evaluator) is a framework that quantifies player-level defensive contributions for every attacking situation in soccer.<n>DEFCON estimates the success probability and expected value of each attacking option, along with each defender's responsibility for stopping it.<n>It assigns positive or negative credits to defenders according to whether they reduced or increased the opponent's Expected Possession Value.
arXiv Detail & Related papers (2025-12-11T07:12:23Z) - Analysis of Line Break prediction models for detecting defensive breakthrough in football [0.0]
In football, attacking teams attempt to break through the opponent's defensive line to create scoring opportunities.<n>This study develops a machine learning model to predict Line Breaks using event and tracking data from the 2023 J1 League season.
arXiv Detail & Related papers (2025-10-31T06:42:20Z) - Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models [64.47869632167284]
Conventional language model (LM) safety alignment relies on a reactive, disjoint procedure: attackers exploit a static model, followed by defensive fine-tuning to patch exposed vulnerabilities.<n>This sequential approach creates a mismatch -- attackers overfit to obsolete defenses, while defenders perpetually lag behind emerging threats.<n>We propose Self-RedTeam, an online self-play reinforcement learning algorithm where an attacker and defender agent co-evolve through continuous interaction.
arXiv Detail & Related papers (2025-06-09T06:35:12Z) - Through the Gaps: Uncovering Tactical Line-Breaking Passes with Clustering [0.0]
Line-breaking passes (LBPs) are crucial tactical actions in football, allowing teams to penetrate defensive lines and access high-value spaces.<n>We present an unsupervised, clustering-based framework for detecting and analysing LBPs using synchronised event and tracking data from elite matches.<n>Our approach models opponent team shape through vertical spatial segmentation and identifies passes that disrupt defensive lines within open play.<n>We evaluate these metrics across teams and players in the 2022 FIFA World Cup, revealing stylistic differences in vertical progression and structural disruption.
arXiv Detail & Related papers (2025-06-07T05:08:24Z) - Benchmarking Misuse Mitigation Against Covert Adversaries [80.74502950627736]
Existing language model safety evaluations focus on overt attacks and low-stakes tasks.<n>We develop Benchmarks for Stateful Defenses (BSD), a data generation pipeline that automates evaluations of covert attacks and corresponding defenses.<n>Our evaluations indicate that decomposition attacks are effective misuse enablers, and highlight stateful defenses as a countermeasure.
arXiv Detail & Related papers (2025-06-06T17:33:33Z) - MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
arXiv Detail & Related papers (2025-06-03T01:37:09Z) - Unveiling Hidden Pivotal Players with GoalNet: A GNN-Based Soccer Player Evaluation System [8.957579200590988]
Soccer analysis tools emphasize metrics such as expected goals, leading to an overrepresentation of attacking players' contributions.<n>We introduce a GNN-based framework that assigns individual credit for changes in expected threat (xT)<n>Our pipeline encodes both spatial and temporal features in event-centric graphs, enabling fair attribution of non-scoring actions.
arXiv Detail & Related papers (2025-03-12T18:36:55Z) - Learn from the Past: A Proxy Guided Adversarial Defense Framework with
Self Distillation Regularization [53.04697800214848]
Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models.
AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting.
We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
arXiv Detail & Related papers (2023-10-19T13:13:41Z) - Cooperation or Competition: Avoiding Player Domination for Multi-Target
Robustness via Adaptive Budgets [76.20705291443208]
We view adversarial attacks as a bargaining game in which different players negotiate to reach an agreement on a joint direction of parameter updating.
We design a novel framework that adjusts the budgets of different adversaries to avoid any player dominance.
Experiments on standard benchmarks show that employing the proposed framework to the existing approaches significantly advances multi-target robustness.
arXiv Detail & Related papers (2023-06-27T14:02:10Z) - Evaluating the Adversarial Robustness of Adaptive Test-time Defenses [60.55448652445904]
We categorize such adaptive testtime defenses and explain their potential benefits and drawbacks.
Unfortunately, none significantly improve upon static models when evaluated appropriately.
Some even weaken the underlying static model while simultaneously increasing inference cost.
arXiv Detail & Related papers (2022-02-28T12:11:40Z) - What Happened Next? Using Deep Learning to Value Defensive Actions in
Football Event-Data [1.290382979353427]
We use deep learning techniques to define a novel metric that values such defensive actions.
By studying the threat of passages of play that preceded them, we are able to value defensive actions.
Our model is able to predict the impact of defensive defenders using event-data.
arXiv Detail & Related papers (2021-06-03T12:18:26Z) - Reliable evaluation of adversarial robustness with an ensemble of
diverse parameter-free attacks [65.20660287833537]
In this paper we propose two extensions of the PGD-attack overcoming failures due to suboptimal step size and problems of the objective function.
We then combine our novel attacks with two complementary existing ones to form a parameter-free, computationally affordable and user-independent ensemble of attacks to test adversarial robustness.
arXiv Detail & Related papers (2020-03-03T18:15:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.