3 citations · 6 across the 13 of their papers we have counts for
13 papers
DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations
Ivoline Ngong, Jack D'Iorio, Hailey Schoppe +4
Systems for speaker anonymization obfuscate the speaker of an utterance, while maintaining its original semantic contents and prosody. Recent solutions for speaker anonymization re…
AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
Ivoline C. Ngong, Keerthiram Murugesan, Swanand Kadhe +3
Agentic systems are increasingly acting on users' behalf, accessing calendars, email, and personal files to complete everyday tasks. Privacy evaluation for these systems has focuse…
Differentially Private Multimodal In-Context Learning
Ivoline C. Ngong, Zarreen Reza, Joseph P. Near
Vision-language models are increasingly applied to sensitive domains such as medical imaging and personal photographs, yet existing differentially private methods for in-context le…
Beyond Fixed Psychological Personas: State Beats Trait, but Language Models are State-Blind
Tamunotonye Harry, Ivoline Ngong, Chima Nweke +2
User interactions with language models vary due to static properties of the user (trait) and the specific context of the interaction (state). However, existing persona datasets (li…
Distributed HDMM: Scalable, Distributed, Accurate, and Differentially Private Query Workloads without a Trusted Curator
Ratang Sedimo, Ivoline C. Ngong, Jami Lashua +1
We present the Distributed High-Dimensional Matrix Mechanism (Distributed HDMM), a protocol for answering workloads of linear queries on distributed data that provides the accuracy…
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
Ivoline Ngong, Swanand Kadhe, Hao Wang +4
Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share informat…
SoK: Usability Studies in Differential Privacy
Onyinye Dibia, Prianka Bhattacharjee, Brad Stenger +5
Differential Privacy (DP) has emerged as a pivotal approach for safeguarding individual privacy in data analysis, yet its practical adoption is often hindered by challenges in the…
Differentially Private Learning Needs Better Model Initialization and Self-Distillation
Ivoline C. Ngong, Joseph P. Near, Niloofar Mireshghallah
Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a th…
Evaluating the Usability of Differential Privacy Tools with Data Practitioners
Ivoline C. Ngong, Brad Stenger, Joseph P. Near +1
Differential privacy (DP) has become the gold standard in privacy-preserving data analytics, but implementing it in real-world datasets and systems remains challenging. Recently de…
OLYMPIA: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols
Ivoline C. Ngong, Nicholas Gibson, Joseph P. Near
Recent secure aggregation protocols enable privacy-preserving federated learning for high-dimensional models among thousands or even millions of participants. Due to the scale of t…
Backpropagation Clipping for Deep Learning with Differential Privacy
Timothy Stevens, Ivoline C. Ngong, David Darais +3
We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning. Our approach clips each tr…
Prediction Sensitivity: Continual Audit of Counterfactual Fairness in Deployed Classifiers
Krystal Maughan, Ivoline C. Ngong, Joseph P. Near
As AI-based systems increasingly impact many areas of our lives, auditing these systems for fairness is an increasingly high-stakes problem. Traditional group fairness metrics can…
Towards Auditability for Fairness in Deep Learning
Ivoline C. Ngong, Krystal Maughan, Joseph P. Near
Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make…