6 papers
Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
Aljalila Aladawi, Mohammed Talha Alam, Fakhri Karray
Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods…
AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
Yichen Jiang, Mohammed Talha Alam, Sohail Ahmed Khan +2
Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specific artifacts as the very definiti…
FaceAnonyMixer: Cancelable Faces via Identity Consistent Latent Space Mixing
Mohammed Talha Alam, Fahad Shamshad, Fakhri Karray +1
Advancements in face recognition (FR) technologies have amplified privacy concerns, necessitating methods that protect identity while maintaining recognition utility. Existing face…
ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions
Fatmah AlHindaassi, Mohammed Talha Alam, Fakhri Karray
Adverse weather conditions, particularly fog, pose a significant challenge to autonomous vehicles, surveillance systems, and other safety-critical applications by severely degradin…
CosmoCLIP: Generalizing Large Vision-Language Models for Astronomical Imaging
Raza Imam, Mohammed Talha Alam, Umaima Rahman +2
Existing vision-text contrastive learning models enhance representation transferability and support zero-shot prediction by matching paired image and caption embeddings while pushi…
Introducing SDICE: An Index for Assessing Diversity of Synthetic Medical Datasets
Mohammed Talha Alam, Raza Imam, Mohammad Areeb Qazi +2
Advancements in generative modeling are pushing the state-of-the-art in synthetic medical image generation. These synthetic images can serve as an effective data augmentation metho…