Research Highlights

Selected research highlights and publications

Research Highlights

Discover our innovative approaches to building robust and secure AI systems

SLADE: Shielding against Dual Exploits in Large Vision-Language Models

Md Zarif Hossain, Ahmed Imteaj
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025 Accepted
Paper Supp Code Poster Slides Video
Research Architecture Overview
Research Architecture Overview: Our novel defense mechanism protects Vision-Language Models against dual exploits through robust encoding and adversarial training techniques.

Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust Vision-Language Models

Md Zarif Hossain, Ahmed Imteaj
arXiv preprint arXiv:2407.14971 Under Review in IEEE Transactions on Big Data
Paper Code Poster
Research Architecture Overview
Research Architecture Overview: Unsupervised approach to enhance Vision-Language Models through Siamese adversarial fine-tuning for improved robustness and semantic richness.

Blockchain-Empowered Cyber-Secure Federated Learning for Trustworthy Edge Computing

Moore, E., Imteaj, A., Md Zarif Hossain, Rezapour, S., Amini, M. H.
IEEE Transactions on Artificial Intelligence Published (Q1 Journal)
Paper Code Poster
Research Architecture Overview
Research Architecture Overview: Blockchain-enhanced framework ensuring privacy and security in distributed machine learning across edge computing environments.

Securing Vision-Language Models Against Jailbreak and Adversarial Attacks

Md Zarif Hossain, Ahmed Imteaj
IEEE International Conference on Big Data (BigData) 2024 Published
Paper Code Poster
Research Architecture Overview
Research Architecture Overview: Comprehensive defense mechanism for Vision-Language Models focusing on robust encoding techniques against various attack vectors.

Towards Trustworthy Autonomous Vehicles with Vision-Language Models Under Adversarial Attacks

Fime, Awal Ahmed, Md Zarif Hossain, Zaman, Saika, Shahid, Abdur R., Imteaj, Ahmed
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop 2025 Accepted
Paper Code Poster
Research Architecture Overview
Research Architecture Overview: Examining the robustness of Vision-Language Models in autonomous vehicle applications under targeted and untargeted adversarial attacks.