Publications by categories in reversed chronological order. Please double check the **bibtex** entries if you need to use them, since they are automatically generated from the template. Will recommend to compare with the google scholar page.
2024
Alpha-Wolves and Alpha-Mammals: Exploring Dictionary Attacks on Iris Recognition Systems
Sudipta Banerjee , Anubhav Jain , Zehua Jiang, Nasir Memon , Julian Togelius , and Arun Ross
In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops , Jan 2024
A dictionary attack in a biometric system entails the use of a small number of strategically generated images or templates to successfully match with a large number of identities, thereby compromising security. We focus on dictionary attacks at the template level, specifically the IrisCodes used in iris recognition systems. We present an hitherto unknown vulnerability wherein we mix IrisCodes using simple bitwise operators to generate alpha-mixtures— alpha-wolves (combining a set of "wolf" samples) and alpha-mammals (combining a set of users selected via search optimization) that increase false matches. We evaluate this vulnerability using the IITD, CASIA-IrisV4-Thousand and Synthetic datasets, and observe that an alpha-wolf (from two wolves) can match upto 71 identities @FMR=0.001%, while an alpha-mammal (from two identities) can match upto 133 other identities @FMR=0.01% on the IITD dataset.
@inproceedings{Banerjee_2024_WACV,author={Banerjee, Sudipta and Jain, Anubhav and Jiang, Zehua and Memon, Nasir and Togelius, Julian and Ross, Arun},title={Alpha-Wolves and Alpha-Mammals: Exploring Dictionary Attacks on Iris Recognition Systems},booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops},month=jan,year={2024},pages={1072-1081},}
2023
Controllable Path of Destruction
Matthew Siper , Sam Earle , Zehua Jiang, Ahmed Khalifa , and Julian Togelius
Path of Destruction (PoD) is a self-supervised method for learning iterative generators. The core idea is to produce a training set by destroying a set of artifacts, and for each destructive step create a training instance based on the corresponding repair action. A generator trained on this dataset can then generate new artifacts by repairing from arbitrary states. The PoD method is very data-efficient in terms of original training examples and well-suited to functional artifacts composed of categorical data, such as game levels and discrete 3D structures. In this paper, we extend the Path of Destruction method to allow designer control over aspects of the generated artifacts. Controllability is introduced by adding conditional inputs to the state-action pairs that make up the repair trajectories. We test the controllable PoD method in a 2D dungeon setting, as well as in the domain of small 3D Lego cars.
@article{siper2023controllable,title={Controllable Path of Destruction},author={Siper, Matthew and Earle, Sam and Jiang, Zehua and Khalifa, Ahmed and Togelius, Julian},journal={arXiv preprint arXiv:2305.18553},year={2023},}
2022
Learning Controllable 3D Level Generators
Zehua Jiang, Sam Earle , Michael Green , and Julian Togelius
In Proceedings of the 17th International Conference on the Foundations of Digital Games , Jan 2022
Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measures of quality instead of target output. We explore the application of PCGRL to 3D domains, in which content-generation tasks naturally have greater complexity and potential pertinence to real-world applications. Here, we introduce several PCGRL tasks for the 3D domain, Minecraft. These tasks will challenge RL-based generators using affordances often found in 3D environments, such as jumping, multiple dimensional movement, and gravity. We train agents to optimize each of these tasks to explore the capabilities of existing in PCGRL. The agents are able to generate relatively complex and diverse levels, and generalize to random initial states and control targets. Controllability tests in the presented tasks demonstrate their utility to analyze success and failure for 3D generators. We argue that these generators could serve both as co-creative tools for game designers, and as pre-trained environment generators in curriculum learning for player agents.
@inproceedings{jiang2022learning,title={Learning Controllable 3D Level Generators},author={Jiang, Zehua and Earle, Sam and Green, Michael and Togelius, Julian},booktitle={Proceedings of the 17th International Conference on the Foundations of Digital Games},pages={1--9},year={2022},}
Diversity and Novelty MasterPrints: Generating Multiple DeepMasterPrints for Increased User Coverage
M Charity , Nasir Memon , Zehua Jiang, Abhi Sen , and Julian Togelius
In 2022 International Conference of the Biometrics Special Interest Group (BIOSIG) , Jan 2022
This work expands on previous advancements in genetic fingerprint spoofing via the DeepMasterPrints and introduces Diversity and Novelty MasterPrints. This system uses quality diversity evolutionary algorithms to generate dictionaries of artificial prints with a focus on increasing coverage of users from the dataset. The Diversity MasterPrints focus on generating solution prints that match with users not covered by previously found prints, and the Novelty MasterPrints explicitly search for prints with more that are farther in user space than previous prints. Our multi-print search methodologies outperform the singular DeepMasterPrints in both coverage and generalization while maintaining quality of the fingerprint image output.
@inproceedings{charity2022diversity,title={Diversity and Novelty MasterPrints: Generating Multiple DeepMasterPrints for Increased User Coverage},author={Charity, M and Memon, Nasir and Jiang, Zehua and Sen, Abhi and Togelius, Julian},booktitle={2022 International Conference of the Biometrics Special Interest Group (BIOSIG)},pages={1--4},year={2022},organization={IEEE},}