7 citations · 18 across the 6 of their papers we have counts for
6 papers
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati +4
Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. H…
On Pretraining Data Diversity for Self-Supervised Learning
Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati +3
We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed comp…
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
Hasan Abed Al Kader Hammoud, Hani Itani, Fabio Pizzati +3
We present SynthCLIP, a CLIP model trained on entirely synthetic text-image pairs. Leveraging recent text-to-image (TTI) networks and large language models (LLM), we generate synth…
Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
Hasan Abed Al Kader Hammoud, Adel Bibi, Philip H. S. Torr +1
In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disp…
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
Hasan Abed Al Kader Hammoud, Shuming Liu, Mohammed Alkhrashi +2
Deep neural networks (DNNs) are vulnerable to a class of attacks called "backdoor attacks", which create an association between a backdoor trigger and a target label the attacker i…
Check Your Other Door! Creating Backdoor Attacks in the Frequency Domain
Hasan Abed Al Kader Hammoud, Bernard Ghanem
Deep Neural Networks (DNNs) are ubiquitous and span a variety of applications ranging from image classification to real-time object detection. As DNN models become more sophisticat…