Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Imteaj, Ahmed"'
Autor:
Hossain, Md Zarif, Imteaj, Ahmed
Large Vision-Language Models (LVLMs), trained on multimodal big datasets, have significantly advanced AI by excelling in vision-language tasks. However, these models remain vulnerable to adversarial attacks, particularly jailbreak attacks, which bypa
Externí odkaz:
http://arxiv.org/abs/2409.07353
The rapid advancement and increasing complexity of pretrained models, exemplified by CLIP, offer significant opportunities as well as challenges for Federated Learning (FL), a critical component of privacy-preserving artificial intelligence. This res
Externí odkaz:
http://arxiv.org/abs/2409.05347
Autor:
Hossain, Md Zarif, Imteaj, Ahmed
Vision-language models (VLMs) have achieved significant strides in recent times specially in multimodal tasks, yet they remain susceptible to adversarial attacks on their vision components. To address this, we propose Sim-CLIP, an unsupervised advers
Externí odkaz:
http://arxiv.org/abs/2407.14971
The widespread adoption of machine learning (ML) across various industries has raised sustainability concerns due to its substantial energy usage and carbon emissions. This issue becomes more pressing in adversarial ML, which focuses on enhancing mod
Externí odkaz:
http://arxiv.org/abs/2403.19009
Autor:
Hossain, Md Zarif, Imteaj, Ahmed
Federated Learning (FL), a distributed machine learning technique has recently experienced tremendous growth in popularity due to its emphasis on user data privacy. However, the distributed computations of FL can result in constrained communication a
Externí odkaz:
http://arxiv.org/abs/2305.01154
Federated Learning (FL) has gained widespread popularity in recent years due to the fast booming of advanced machine learning and artificial intelligence along with emerging security and privacy threats. FL enables efficient model generation from loc
Externí odkaz:
http://arxiv.org/abs/2303.13727
Publikováno v:
2021 Innovations in Intelligent Systems and Applications Conference (ASYU)
Clustering is one of the widely used techniques to find out patterns from a dataset that can be applied in different applications or analyses. K-means, the most popular and simple clustering algorithm, might get trapped into local minima if not prope
Externí odkaz:
http://arxiv.org/abs/2210.09507
Human Activity Recognition (HAR) is a problem of interpreting sensor data to human movement using an efficient machine learning (ML) approach. The HAR systems rely on data from untrusted users, making them susceptible to data poisoning attacks. In a
Externí odkaz:
http://arxiv.org/abs/2208.08433
Autor:
Imteaj, Ahmed, Amini, M. Hadi
Smartphones, autonomous vehicles, and the Internet-of-things (IoT) devices are considered the primary data source for a distributed network. Due to a revolutionary breakthrough in internet availability and continuous improvement of the IoT devices ca
Externí odkaz:
http://arxiv.org/abs/2101.03705