WakaTime: Broken Access Control Exposes Email Verification Status and Privacy Settings via API Endpoint

The /api/v1/users/username endpoint leaked sensitive email-related metadata, such as the user's email confirmation status and privacy settings, without proper authorization checks. This allowed attackers to determine whether an account's email address was confirmed and the user's email privacy...

SONNI: Secure Oblivious Neural Network Inference

In the standard privacy-preserving Machine learning as-a-service MLaaS model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It has become more and more common for the computation to be...

Differentially Private Quasi-Concave Optimization: Bypassing the Lower Bound and Application to Geometric Problems

Whitepaper called Differentially Private Quasi-Concave Optimization: Bypassing The Lower Bound And Application To Geometric Problems...

CVE-2025-3645 Moodle: idor in messaging web service allows access to some user details

A flaw was found in Moodle. Insufficient capability checks in a messaging web service allowed users to view other users' names and online statuses...

CVE-2025-3640 Moodle: idor in web service allows users enrolled in a course to access some details of other users

A flaw was found in Moodle. Insufficient capability checks made it possible for a user enrolled in a course to access some details, such as the full name and profile image URL, of other users they did not have permission to access...

DeSIA: Attribute Inference Attacks against Limited Fixed Aggregate Statistics

Empirical inference attacks are a popular approach for evaluating the privacy risk of data release mechanisms in practice. While an active attack literature exists to evaluate machine learning models or synthetic data release, we currently lack comparable methods for fixed aggregate statistics, i...

NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation

Large Language Models LLM are typically trained on vast amounts of data from various sources. Even when designed modularly e.g., Mixture-of-Experts, LLMs can leak privacy on their sources. Conversely, training such models in isolation arguably prohibits generalization. To this end, we propose a...

Heavy-Tailed Privacy: the Symmetric Alpha-Stable Privacy Mechanism

With the rapid growth of digital platforms, there is increasing apprehension about how personal data is collected, stored, and used by various entities. These concerns arise from the increasing frequency of data breaches, cyber-attacks, and misuse of personal information for targeted advertising...

Protecting Your Phone—and Your Privacy—at the US Border

In this episode of Uncanny Valley, our hosts explain how to prepare for travel to and from the United States—and how to stay safe...

Blue Shield Leaked Millions of Patient Info to Google for Years

Blue Shield of California exposed the health data of 4.7 million members to Google for years due to…...

WhatsApp Adds Advanced Chat Privacy to Blocks Chat Exports and Auto-Downloads

WhatsApp has introduced an extra layer of privacy called Advanced Chat Privacy that allows users to block participants from sharing the contents of a conversation in traditional chats and groups. "This new setting available in both chats and groups helps prevent others from taking content outside...

Silenzio: Secure Non-Interactive Outsourced MLP Training

Outsourcing the ML training to cloud providers presents a compelling opportunity for resource constrained clients, while it simultaneously bears inherent privacy risks, especially for highly sensitive training data. We introduce Silenzio, the first fully non-interactive outsourcing scheme for the...

Differential Privacy-Driven Framework for Enhancing Heart Disease Prediction

With the rapid digitalization of healthcare systems, there has been a substantial increase in the generation and sharing of private health data. Safeguarding patient information is essential for maintaining consumer trust and ensuring compliance with legal data protection regulations. Machine...

Optimizing the Privacy-Utility Balance Using Synthetic Data and Configurable Perturbation Pipelines

This paper explores the strategic use of modern synthetic data generation and advanced data perturbation techniques to enhance security, maintain analytical utility, and improve operational efficiency when managing large datasets, with a particular focus on the Banking, Financial Services, and...

From Randomized Response to Randomized Index: Answering Subset Counting Queries with Local Differential Privacy

Local Differential Privacy LDP is the predominant privacy model for safeguarding individual data privacy. Existing perturbation mechanisms typically require perturbing the original values to ensure acceptable privacy, which inevitably results in value distortion and utility deterioration. In this...

Shopify faces privacy lawsuit for collecting customer data

Shopify faces a data privacy class action lawsuit in the US that could change the way globally active companies can be held accountable. The proposed class action is a revival of a case that had been dismissed by a lower court judge and a three-judge 9th Circuit Court of Appeals panel. But now it...

Lattica Emerges from Stealth to Solve AI’s Biggest Privacy Challenge with FHE

Lattica’s cloud-based solution uses Fully Homomorphic Encryption to query encrypted data on AI models without decrypting it, preserving privacy and bolstering security...

Google Drops Cookie Prompt in Chrome, Adds IP Protection to Incognito

Google on Tuesday revealed that it will no longer offer a standalone prompt for third-party cookies in its Chrome browser as part of its Privacy Sandbox initiative. "We've made the decision to maintain our current approach to offering users third-party cookie choice in Chrome, and will not be...

Developing a Blockchain-Based Secure Digital Contents Distribution System

As digital content distribution expands rapidly through online platforms, securing digital media and protecting intellectual property has become increasingly complex. Traditional centralized systems, while widely adopted, suffer from vulnerabilities such as single points of failure and limited...

Private Federated Learning Using Preference-Optimized Synthetic Data

In practical settings, differentially private Federated learning DP-FL is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data Wu et al., 2024; Hou et al., 2024. The...