Skip to content

Author

Mohamed Elmahallawy

We have 9 of 38 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Where Can We Fool the Model's Mind? Response-Guided Semantic Probing and Adaptive Routing for Transferable Attacks on Black-Box MLLMs

Multimodal Large Language Models (MLLMs) ground language in visual evidence, yet their semantic reasoning can be exploited through transferable black-box adversarial attacks. Existing attacks typically allocate perturbations using surrogate-model saliency, which may not reflect how an unseen MLLM semantically interpret...

A. Abdel-Naby, Mohamed Elmahallawy · 0 citations
#natural language process... Preprint Oct 2026

Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction

Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers exposes data subjects and organizations to risks from logging, retention, model training, and unintended disclosure. Existing anony...

Mohamed Elmahallawy, M. Shaaban, Thomas E. Carroll · 0 citations
#artificial intelligence Preprint Oct 2026

Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning

JEPA-Prune is proposed, a post-hoc neuron pruning framework guided by a model trained exclusively on PII-free views, which trains a public model on surrogate and masked views of the same records using a joint-embedding predictive architecture (JEPA), capturing domain knowledge without identifiers.

M. Shaaban, Mohamed Elmahallawy · 0 citations
Preprint Sep 2026

Label Less, Learn More: Resource-Efficient Active Semi-Supervised Learning for Onboard Satellite Image Annotation

Large-scale pervasive sensing increasingly relies on high-resolution satellite imagery, yet task-specific onboard vision is constrained by costly annotation and limited computation, memory, energy, and communication resources. Existing approaches largely rely on either data-hungry supervised learning or large vision-la...

A. Abdel-Naby, Mohamed Elmahallawy, Marius Bernahrndt et al. · 0 citations
#artificial intelligence Open access Sep 2026

Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs

Large language models (LLMs) are increasingly deployed in privacy-critical domains (e.g., healthcare, finance, and government), but their propensity to memorize and disclose personally identifiable information (PII) poses serious security and compliance risks. Existing defenses typically force a trade-off between model...

M. Shaaban, Mohamed Elmahallawy · 0 citations

Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations

Low-Earth-orbit (LEO) satellites are increasingly expected to perform onboard learning for applications such as disaster response and environmental monitoring. However, conventional federated learning (FL) is ill-suited to onboard satellite learning, as it assumes computational, memory, and communication resources beyo...

M. Shaaban, Mohamed Elmahallawy, Marius Bernahrndt et al. · 0 citations
#small language model Conference Open access Sep 2026

Region-Level Black-Box Defense Against Stealthy Embedding-Space Backdoors in CLIP

CLIPGuard is proposed, a lightweight and fully black-box defense specifically designed to mitigate embedding-space backdoors in CLIP encoders, consistently outperforming existing black-box defenses, including CleanCLIP and CleanerCLIP.

A. Abdel-Naby, Mohamed Elmahallawy · 1 citation

When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense

Federated Learning enables decentralized model training by exchanging model updates--rather than raw data--with a central parameter server (PS). While most of the existing defenses primarily assume static or independently acting adversaries, we reveal a new class of dynamically adaptive attacks that systematically bypa...

M. Shaaban, A. Abdel-Naby, Mohamed Elmahallawy · 0 citations
Preprint Sep 2026

Beyond Small Patches: Black-Box Detection and Purification of Diverse Backdoor Triggers

TRIM (Trigger Removal by Identifying Manipulated Regions), a deployment-oriented black-box defense that detects and selectively removes backdoor triggers at inference time without requiring model internals, training data, or clean samples, is proposed.

A. Abdel-Naby, Mohamed Elmahallawy · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.