Eman El-Sheikh
YOU?
Author Swipe
View article: Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning
Adaptive Additive Parameter Updates of Vision Transformers for Few-Shot Continual Learning Open
Integrating new class information without losing previously acquired knowledge remains a central challenge in artificial intelligence, often referred to as catastrophic forgetting. Few-shot class incremental learning (FSCIL) addresses this…
View article: Transductive One-Shot Learning Meet Subspace Decomposition
Transductive One-Shot Learning Meet Subspace Decomposition Open
One-shot learning focuses on adapting pretrained models to recognize newly introduced and unseen classes based on a single labeled image. While variations of few-shot and zero-shot learning exist, one-shot learning remains a challenging ye…
View article: Visual Adaptive Prompting for Compositional Zero-Shot Learning
Visual Adaptive Prompting for Compositional Zero-Shot Learning Open
Vision-Language Models (VLMs) have demonstrated impressive multimodal capabilities in learning joint representations of visual and textual data, making them powerful tools for tasks such as Compositional Zero-Shot Learning (CZSL). CZSL req…
View article: Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection With Few Samples
Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection With Few Samples Open
As networks continue to expand and become more interconnected, the need for novel malware detection methods becomes more pronounced. Traditional security measures are increasingly inadequate against the sophistication of modern cyber attac…
View article: Proactive Disentangled Modeling of Trigger–Object Pairings for Backdoor Defense
Proactive Disentangled Modeling of Trigger–Object Pairings for Backdoor Defense Open
Deep neural networks (DNNs) and generative AI (GenAI) are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional single-tri…
View article: Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images Open
Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through …
View article: Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samples
Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samples Open
As networks continue to expand and become more interconnected, the need for novel malware detection methods becomes more pronounced. Traditional security measures are increasingly inadequate against the sophistication of modern cyber attac…
View article: Towards Novel Malicious Packet Recognition: A Few-Shot Learning Approach
Towards Novel Malicious Packet Recognition: A Few-Shot Learning Approach Open
As the complexity and connectivity of networks increase, the need for novel malware detection approaches becomes imperative. Traditional security defenses are becoming less effective against the advanced tactics of today's cyberattacks. De…
View article: A Transformer-Based Framework for Payload Malware Detection and Classification
A Transformer-Based Framework for Payload Malware Detection and Classification Open
As malicious cyber threats become more sophisticated in breaching computer networks, the need for effective intrusion detection systems (IDSs) becomes crucial. Techniques such as Deep Packet Inspection (DPI) have been introduced to allow I…
View article: A Multi-Stage Detection Technique for DNS-Tunneled Botnets
A Multi-Stage Detection Technique for DNS-Tunneled Botnets Open
Botnet communications are obfuscated within legitimate network protocols to avoid detection and remediation. Domain Name Service (DNS) is a protocol of choice to hide communication with Command & Control (C&C) servers, where botmas…