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...
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
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.
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
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· IEEE Transactions on Artific...· 0 citations
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.· arXiv.org· 0 citations
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· Pacific-Asia Conference on K...· 1 citation
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· arXiv.org· 0 citations
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.