Robust Optimization with Diffusion Models for Green Security

Lingkai Kong, Haichuan Wang, Yuqi Pan, Cheol Woo Kim, Mingxiao Song, Alayna Nguyen, Tonghan Wang, Haifeng Xu, Milind Tambe
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:2325-2344, 2025.

Abstract

In green security, defenders must forecast adversarial behavior-such as poaching, illegal logging, and illegal fishing-to plan effective patrols. These behavior are often highly uncertain and complex. Prior work has leveraged game theory to design robust patrol strategies to handle uncertainty, but existing adversarial behavior models primarily rely on Gaussian processes or linear models, which lack the expressiveness needed to capture intricate behavioral patterns. To address this limitation, we propose a conditional diffusion model for adversary behavior modeling, leveraging its strong distribution-fitting capabilities. To the best of our knowledge, this is the first application of diffusion models in the green security domain. Integrating diffusion models into game-theoretic optimization, however, presents new challenges, including a constrained mixed strategy space and the need to sample from an unnormalized distribution to estimate utilities. To tackle these challenges, we introduce a mixed strategy of mixed strategies and employ a twisted Sequential Monte Carlo (SMC) sampler for accurate sampling. Theoretically, our algorithm is guaranteed to converge to an \(\epsilon\)-equilibrium with high probability using a finite number of iterations and samples. Empirically, we evaluate our approach on both synthetic and real-world poaching datasets, demonstrating its effectiveness.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-kong25c, title = {Robust Optimization with Diffusion Models for Green Security}, author = {Kong, Lingkai and Wang, Haichuan and Pan, Yuqi and Kim, Cheol Woo and Song, Mingxiao and Nguyen, Alayna and Wang, Tonghan and Xu, Haifeng and Tambe, Milind}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {2325--2344}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/kong25c/kong25c.pdf}, url = {https://proceedings.mlr.press/v286/kong25c.html}, abstract = {In green security, defenders must forecast adversarial behavior-such as poaching, illegal logging, and illegal fishing-to plan effective patrols. These behavior are often highly uncertain and complex. Prior work has leveraged game theory to design robust patrol strategies to handle uncertainty, but existing adversarial behavior models primarily rely on Gaussian processes or linear models, which lack the expressiveness needed to capture intricate behavioral patterns. To address this limitation, we propose a conditional diffusion model for adversary behavior modeling, leveraging its strong distribution-fitting capabilities. To the best of our knowledge, this is the first application of diffusion models in the green security domain. Integrating diffusion models into game-theoretic optimization, however, presents new challenges, including a constrained mixed strategy space and the need to sample from an unnormalized distribution to estimate utilities. To tackle these challenges, we introduce a mixed strategy of mixed strategies and employ a twisted Sequential Monte Carlo (SMC) sampler for accurate sampling. Theoretically, our algorithm is guaranteed to converge to an \(\epsilon\)-equilibrium with high probability using a finite number of iterations and samples. Empirically, we evaluate our approach on both synthetic and real-world poaching datasets, demonstrating its effectiveness.} }
Endnote
%0 Conference Paper %T Robust Optimization with Diffusion Models for Green Security %A Lingkai Kong %A Haichuan Wang %A Yuqi Pan %A Cheol Woo Kim %A Mingxiao Song %A Alayna Nguyen %A Tonghan Wang %A Haifeng Xu %A Milind Tambe %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-kong25c %I PMLR %P 2325--2344 %U https://proceedings.mlr.press/v286/kong25c.html %V 286 %X In green security, defenders must forecast adversarial behavior-such as poaching, illegal logging, and illegal fishing-to plan effective patrols. These behavior are often highly uncertain and complex. Prior work has leveraged game theory to design robust patrol strategies to handle uncertainty, but existing adversarial behavior models primarily rely on Gaussian processes or linear models, which lack the expressiveness needed to capture intricate behavioral patterns. To address this limitation, we propose a conditional diffusion model for adversary behavior modeling, leveraging its strong distribution-fitting capabilities. To the best of our knowledge, this is the first application of diffusion models in the green security domain. Integrating diffusion models into game-theoretic optimization, however, presents new challenges, including a constrained mixed strategy space and the need to sample from an unnormalized distribution to estimate utilities. To tackle these challenges, we introduce a mixed strategy of mixed strategies and employ a twisted Sequential Monte Carlo (SMC) sampler for accurate sampling. Theoretically, our algorithm is guaranteed to converge to an \(\epsilon\)-equilibrium with high probability using a finite number of iterations and samples. Empirically, we evaluate our approach on both synthetic and real-world poaching datasets, demonstrating its effectiveness.
APA
Kong, L., Wang, H., Pan, Y., Kim, C.W., Song, M., Nguyen, A., Wang, T., Xu, H. & Tambe, M.. (2025). Robust Optimization with Diffusion Models for Green Security. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:2325-2344 Available from https://proceedings.mlr.press/v286/kong25c.html.

Related Material