Portrait of Adel Abusitta

Adel Abusitta

Associate Academic Member
adel.abusitta@mila.quebec
Assistant professor, Polytechnique Montréal
Research Topics
AI Safety
Applied AI
Deep Learning
Disinformation
Explainable AI (XAI)
Reinforcement Learning
Representation Learning
Trustworthy AI
Google Scholar
LinkedIn

Biography

Dr. Adel Abusitta is an Assistant Professor at Polytechnique Montréal and an Associate Academic Member at Mila. He is the Founding Director of the Security and Trustworthy AI (STAI) Lab. His research focuses on AI security, AI-powered cybersecurity, and trustworthy artificial intelligence, with particular interests in securing generative AI and autonomous AI agents, adversarial machine learning, and privacy-preserving AI.

He leads and contributes to research projects supported by the Natural Sciences and Engineering Research Council of Canada (NSERC), including NSERC Alliance grants in partnership with the Communications Security Establishment (CSE), as well as the Fonds de recherche du Québec (FRQ) and Mitacs. His work aims to develop practical solutions for building secure, resilient, and trustworthy AI systems.

Current Students

Francesco Morri
Postdoctorate - Polytechnique Montréal
Co-supervisor :
Margarida Carvalho
francesco98m@gmail.com
Website
Github
Google Scholar

Publications

Cooperation Without Shared Rewards via Reciprocal Q-Augmentation
Francesco Morri
Adel Abusitta
Quentin Cappart
Margarida Carvalho
General-sum games are more challenging than fully cooperative or adversarial settings because agents may deceive or exploit one another. Ach… (see more)ieving high social welfare requires sustained cooperation, while a single defection can drive agents toward a welfare suboptimal Nash equilibrium. Moreover, assuming access to other agents' rewards or internal states is often unrealistic and implicitly introduces additional cooperation into the setting. To address this issue, we introduce \textit{Reciprocal Q-Augmentation} (RQA), a method that uses a latent-variable opponent model to augment the Q-function with estimates of how one's actions affects other agents. RQA allows agents to learn both cooperative and defective policies using only their own Q-function. We show that, in social dilemmas, agents that all follow the cooperative policy of RQA learn to cooperate faster and reach higher levels of cooperation than fully cooperative algorithms. Moreover, a single RQA agent that switches appropriately between its cooperative and defecting policies can induce cooperation in agents trained with standard RL algorithms, which would otherwise end up defecting. We evaluate our approach on the Iterated Prisoner's Dilemma, Iterated Traveler's Dilemma, Iterated Stag Hunt, and \texttt{CleanUp-Lite}. Our experiments show that the algorithms implementing RQA outperforms fully cooperative methods with shared rewards and enables cooperation with algorithms that otherwise fail to reach high social welfare.
2026-10-16
arXiv (preprint)
doi.org
arxiv.org
CSGraph2Vec: Distributed Graph-Based Representation Learning for Assembly Functions
Wael J. Alhashemi
Benjamin C. M. Fung
Adel Abusitta
Claude Fachkha
2024-11-05
2024 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE) (published)
doi.org
Survey on Explainable AI: Techniques, challenges and open issues
Adel Abusitta
Miles Q. Li
Benjamin C. M. Fung
2024-06-30
Expert systems with applications (published)
doi.org
Deep learning-enabled anomaly detection for IoT systems
Adel Abusitta 0001
Adel Abusitta
Glaucio H.S. Carvalho
Omar Abdel Wahab
Talal Halabi
Benjamin C. M. Fung
Saja Al-Mamoori
2022-11-30
Internet of Things (published)
doi.org
On the Effectiveness of Interpretable Feedforward Neural Network
Miles Q. Li
Benjamin C. M. Fung
Adel Abusitta
Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an explan… (see more)ation for their classification results. Machine learning models that are interpretable are usually linear or piecewise linear and yield inferior performance. Non-linear models achieve much better classification performance, but it is usually hard to explain their classification results. As a counter-example, an interpretable feedforward neural network (IFFNN) is proposed to achieve both high classification performance and interpretability for malware detection. If the IFFNN can perform well in a more flexible and general form for other classification tasks while providing meaningful explanations, it may be of great interest to the applied machine learning community. In this paper, we propose a way to generalize the interpretable feedforward neural network to multi-class classification scenarios and any type of feedforward neural networks, and evaluate its classification performance and interpretability on interpretable datasets. We conclude by finding that the generalized IFFNNs achieve comparable classification performance to their normal feedforward neural network counterparts and provide meaningful explanations. Thus, this kind of neural network architecture has great practical use.
2022-07-17
2022 International Joint Conference on Neural Networks (IJCNN) (published)
doi.org
arxiv.org
Incentivized Security-Aware Computation Offloading for Large-Scale Internet of Things Applications
Talal Halabi
Adel Abusitta
Glaucio H.S. Carvalho
Benjamin C. M. Fung
2022-07-04
2022 7th International Conference on Smart and Sustainable Technologies (SpliTech) (published)
doi.org
VirtualGAN: Reducing Mode Collapse in Generative Adversarial Networks Using Virtual Mapping
Adel Abusitta
Omar Abdel Wahab
Benjamin C. M. Fung
This paper introduces a new framework for reducing mode collapse in Generative adversarial networks (GANs). The problem occurs when the gene… (see more)rator learns to map several various input values (z) to the same output value, which makes the generator fail to capture all modes of the true data distribution. As a result, the diversity of synthetically produced data is lower than that of the real data. To address this problem, we propose a new and simple framework for training GANs based on the concept of virtual mapping. Our framework integrates two processes into GANs: merge and split. The merge process merges multiple data points (samples) into one before training the discriminator. In this way, the generator would be trained to capture the merged-data distribution rather than the (unmerged) data distribution. After the training, the split process is applied to the generator's output in order to split its contents and produce diverse modes. The proposed framework increases the chance of capturing diverse modes through enabling an indirect or virtual mapping between an input z value and multiple data points. This, in turn, enhances the chance of generating more diverse modes. Our results show the effectiveness of our framework compared to the existing approaches in terms of reducing the mode collapse problem.
2021-07-17
IEEE International Joint Conference on Neural Network (published)
doi.org