activity
20242026
most citedMANDERA: Malicious Node Detection in Federated Learning via Ranking

2 citations · 2 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CR2026

Protecting User Prompts Via Character-Level Differential Privacy

Shashie Dilhara Batan Arachchige, Hassan Jameel Asghar, Benjamin Zi Hao Zhao +2

Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personally identifiable information…

cs.LG20262 cited

MANDERA: Malicious Node Detection in Federated Learning via Ranking

Wanchuang Zhu, Benjamin Zi Hao Zhao, Simon Luo +2

Byzantine attacks hinder the deployment of federated learning algorithms. Although we know that the benign gradients and Byzantine attacked gradients are distributed differently, t…

cs.CR2025

-Privacy for Text and the Curse of Dimensionality

Hassan Jameel Asghar, Robin Carpentier, Benjamin Zi Hao Zhao +1

A widely used method to ensure privacy of unstructured text data is the multidimensional Laplace mechanism for -privacy, which is a relaxation of differential privacy for metr…

cs.CR2025

Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions

Robin Carpentier, Benjamin Zi Hao Zhao, Hassan Jameel Asghar +1

Interactions with online Large Language Models raise privacy issues where providers can gather sensitive information about users and their companies from the prompts. While textual…

cs.CV2024

Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs

Chenhan Zhang, Benjamin Zi Hao Zhao, Hassan Asghar +1

Users may inadvertently upload personally identifiable information (PII) to Machine Learning as a Service (MLaaS) providers. When users no longer want their PII on these services,…

cs.SI2024

GPTs Window Shopping: An analysis of the Landscape of Custom ChatGPT Models

Benjamin Zi Hao Zhao, Muhammad Ikram, Mohamed Ali Kaafar

OpenAI's ChatGPT initiated a wave of technical iterations in the space of Large Language Models (LLMs) by demonstrating the capability and disruptive power of LLMs. OpenAI has prom…