Media Summary: Less is More: Revisiting the Gaussian Mechanism for Tianhao Wang, Jeremiah Blocki, and Ninghui Li, Purdue University; Somesh Jha, University of Wisconsin Madison Protocols ... Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD Anvith Thudi and Hengrui Jia, University of Toronto and ...

Usenix Security 24 Dpadapter Improving Differentially Private Deep Learning Through Noise - Detailed Analysis & Overview

Less is More: Revisiting the Gaussian Mechanism for Tianhao Wang, Jeremiah Blocki, and Ninghui Li, Purdue University; Somesh Jha, University of Wisconsin Madison Protocols ... Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD Anvith Thudi and Hengrui Jia, University of Toronto and ...

Photo Gallery

USENIX Security '24 - DPAdapter: Improving Differentially Private Deep Learning through Noise...
USENIX Security '23 - PrivateFL: Accurate, Differentially Private Federated Learning via...
USENIX Security '21 - PrivSyn: Differentially Private Data Synthesis
USENIX Security '19 - Evaluating Differentially Private Machine Learning in Practice
USENIX Security '24 - How Does a Deep Learning Model Architecture Impact Its Privacy?...
USENIX Security '24 - dp-promise: Differentially Private Diffusion Probabilistic Models for Image...
USENIX Security '23 - Tight Auditing of Differentially Private Machine Learning
USENIX Security '24 - Efficient Privacy Auditing in Federated Learning
USENIX Security '24 - Less is More: Revisiting the Gaussian Mechanism for Differential Privacy
PEPR '24 - Utility Analysis for Differentially-Private Pipelines
USENIX Security '19 - When the Signal is in the Noise: Exploiting Diffix's Sticky Noise
USENIX Security '17 - Locally Differentially Private Protocols for Frequency Estimation
Sponsored
Sponsored
View Detailed Profile
USENIX Security '24 - DPAdapter: Improving Differentially Private Deep Learning through Noise...

USENIX Security '24 - DPAdapter: Improving Differentially Private Deep Learning through Noise...

DPAdapter

USENIX Security '23 - PrivateFL: Accurate, Differentially Private Federated Learning via...

USENIX Security '23 - PrivateFL: Accurate, Differentially Private Federated Learning via...

USENIX Security

Sponsored
USENIX Security '21 - PrivSyn: Differentially Private Data Synthesis

USENIX Security '21 - PrivSyn: Differentially Private Data Synthesis

USENIX Security

USENIX Security '19 - Evaluating Differentially Private Machine Learning in Practice

USENIX Security '19 - Evaluating Differentially Private Machine Learning in Practice

Evaluating

USENIX Security '24 - How Does a Deep Learning Model Architecture Impact Its Privacy?...

USENIX Security '24 - How Does a Deep Learning Model Architecture Impact Its Privacy?...

How Does a

Sponsored
USENIX Security '24 - dp-promise: Differentially Private Diffusion Probabilistic Models for Image...

USENIX Security '24 - dp-promise: Differentially Private Diffusion Probabilistic Models for Image...

dp-promise:

USENIX Security '23 - Tight Auditing of Differentially Private Machine Learning

USENIX Security '23 - Tight Auditing of Differentially Private Machine Learning

USENIX Security

USENIX Security '24 - Efficient Privacy Auditing in Federated Learning

USENIX Security '24 - Efficient Privacy Auditing in Federated Learning

Efficient Privacy Auditing in Federated

USENIX Security '24 - Less is More: Revisiting the Gaussian Mechanism for Differential Privacy

USENIX Security '24 - Less is More: Revisiting the Gaussian Mechanism for Differential Privacy

Less is More: Revisiting the Gaussian Mechanism for

PEPR '24 - Utility Analysis for Differentially-Private Pipelines

PEPR '24 - Utility Analysis for Differentially-Private Pipelines

PEPR '

USENIX Security '19 - When the Signal is in the Noise: Exploiting Diffix's Sticky Noise

USENIX Security '19 - When the Signal is in the Noise: Exploiting Diffix's Sticky Noise

When the Signal is in the

USENIX Security '17 - Locally Differentially Private Protocols for Frequency Estimation

USENIX Security '17 - Locally Differentially Private Protocols for Frequency Estimation

Tianhao Wang, Jeremiah Blocki, and Ninghui Li, Purdue University; Somesh Jha, University of Wisconsin Madison Protocols ...

USENIX Security '20 - Differentially-Private Control-Flow Node Coverage for Software Usage Analysis

USENIX Security '20 - Differentially-Private Control-Flow Node Coverage for Software Usage Analysis

Differentially

USENIX Security '24 - Privacy Side Channels in Machine Learning Systems

USENIX Security '24 - Privacy Side Channels in Machine Learning Systems

Privacy Side Channels in

PEPR '24 - Through the Lens of LLMs: Unveiling Differential Privacy Challenges

PEPR '24 - Through the Lens of LLMs: Unveiling Differential Privacy Challenges

PEPR '

USENIX Security '21 - Data Poisoning Attacks to Local Differential Privacy Protocols

USENIX Security '21 - Data Poisoning Attacks to Local Differential Privacy Protocols

USENIX Security

PEPR '20 - Improving Usability of Differential Privacy at Scale

PEPR '20 - Improving Usability of Differential Privacy at Scale

Improving

USENIX Security '24 - Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD

USENIX Security '24 - Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD Anvith Thudi and Hengrui Jia, University of Toronto and ...

USENIX Security '19 - Utility-Optimized Local Differential Privacy Mechanisms for

USENIX Security '19 - Utility-Optimized Local Differential Privacy Mechanisms for

Utility-Optimized Local

USENIX Security '24 - DEEPTYPE: Refining Indirect Call Targets with Strong Multi-layer Type Analysis

USENIX Security '24 - DEEPTYPE: Refining Indirect Call Targets with Strong Multi-layer Type Analysis

DEEPTYPE: Refining Indirect Call Targets