DP SGD
PulseAugur coverage of DP SGD — every cluster mentioning DP SGD across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
DP-SGD faces fundamental privacy-utility trade-off limitations
A new research paper published on arXiv details fundamental limitations in Differentially Private Stochastic Gradient Descent (DP-SGD), a common method for private model training. The study, analyzing DP-SGD under the $…
-
New method StraightDP enhances differential privacy for generative models
Researchers have developed StraightDP, a novel method for differentially private training of text-conditioned generative models. This approach addresses the utility cliff often encountered with strong privacy settings b…
-
New optimizer DP-IVON-Gradsq enhances differential privacy in Bayesian deep learning
Researchers have developed DP-IVON-Gradsq, a new optimizer designed to enhance differential privacy in Bayesian deep learning. This method aims to mitigate the interference between privacy noise and the stochasticity in…
-
New technique improves DP-SGD accuracy using model curvature
Researchers have developed a new technique called NoiseCurve to improve the accuracy of differentially private stochastic gradient descent (DP-SGD). This method uses model curvature, estimated from unlabeled data, to en…
-
New methods enhance differential privacy in deep neural network training · 2 sources tracked
Two new research papers propose novel methods for training deep neural networks with differential privacy, aiming to improve both accuracy and efficiency. The first paper introduces an end-to-end framework that privatiz…
-
New metric PCER audits fairness in differentially private ML
Researchers have introduced a new group fairness criterion called the Privacy-Cost Equity Ratio (PCER) for differentially private machine learning systems. PCER addresses the issue that differential privacy mechanisms l…
-
New Dithered Gaussian Mechanism enhances differential privacy efficiency
Researchers have introduced the Dithered Gaussian Mechanism, a new approach to differential privacy that enhances security and efficiency. This method discretizes the private output rather than the noise distribution, i…
-
ICML 2026: AI research advances in efficiency, theory, and robustness
Multiple research papers presented at ICML 2026 explore advancements in AI, focusing on efficiency, robustness, and new theoretical frameworks. Key developments include novel methods for accelerating deep learning opera…
-
New method improves privacy loss accounting for AI algorithms
Researchers have developed a new method for efficiently calculating privacy loss in differentially private algorithms, particularly those involving subsampling and random allocation. This approach, detailed in a recent …
-
New DP-NGD framework boosts privacy-preserving ML utility and speed · 2 sources tracked
Researchers have developed DP-NGD, a novel framework for differentially private natural gradient descent that aims to improve the utility of privacy-preserving machine learning. Unlike standard DP-SGD which ignores loss…
-
New RaCO-DP method enhances private learning with fairness constraints
Researchers have developed RaCO-DP, a novel method for optimizing machine learning models under differential privacy while adhering to rate constraints. This approach addresses challenges in applying standard DP techniq…
-
Research: DP SGD ineffective for SLM memorization reduction in CSIRT data
A new research paper explores methods to reduce memorization in small language models (SLMs) when fine-tuned on sensitive data from Computer Security Incident Response Teams (CSIRTs). The study found that while Differen…
-
New DP learning framework uses hypernetwork to reduce noise impact
Researchers have developed a novel framework for differentially private (DP) learning that bypasses iterative parameter-space optimization. Instead of using privatized gradients, the method employs a hypernetwork traine…
-
New auditors improve f-Differential Privacy assessment without fixed sample size
Researchers have developed new auditors to empirically assess the Differential Privacy (DP) of algorithms, focusing on the expressive $f$-DP concept. These auditors can detect privacy violations across the full privacy …
-
New papers explore differential privacy in Gaussian Processes and ML reporting
Two recent arXiv papers explore differential privacy in machine learning, focusing on Gaussian processes and reporting mechanisms. The first paper details how the intrinsic randomness of Gaussian Process posterior sampl…
-
New TRAP benchmark reveals AI agents leak sensitive data, proposes isolation solution · 3 sources tracked
Researchers have introduced TRAP, a new benchmark designed to evaluate AI agents' ability to complete tasks while resisting privacy extraction. The benchmark assesses the trade-off between task accuracy and data leakage…
-
Federated autoencoder enhances ECG anomaly detection with privacy on edge devices
Researchers have developed a privacy-preserving federated autoencoder system for detecting anomalies in electrocardiogram (ECG) data on edge devices. The system combines federated learning with differential privacy and …
-
New research papers explore robust privacy and differential privacy in ML
Two new research papers explore advanced privacy techniques for machine learning models. The first paper introduces "Robust Privacy" (RP), a method that leverages certified robustness to protect sensitive attributes dur…
-
EEG Foundation Models Leak Data Despite Standard Audits
Researchers have developed a new auditing framework for EEG foundation models that goes beyond single-endpoint evaluations. This framework jointly audits multiple endpoints, revealing that models cleared by individual t…
-
New DP-SGD method updates fewer coordinates for efficiency
Researchers have developed a new method called TP-TopK DP-SGD to improve the efficiency of differentially private stochastic gradient descent. This technique aims to reduce the computational overhead by updating fewer c…