Differentially Private Explanations for Clusters

The dire need to protect sensitive data has led to various flavors of privacy definitions. Among these, Differential privacy DP is considered one of the most rigorous and secure notions of privacy, enabling data analysis while preserving the privacy of data contributors. One of the fundamental...

QualitEye: Public and Privacy-Preserving Gaze Data Quality Verification

Gaze-based applications are increasingly advancing with the availability of large datasets but ensuring data quality presents a substantial challenge when collecting data at scale. It further requires different parties to collaborate, therefore, privacy concerns arise. We propose QualitEye--the...

A Certified Unlearning Approach without Access to Source Data

With the growing adoption of data privacy regulations, the ability to erase private or copyrighted information from trained models has become a crucial requirement. Traditional unlearning methods often assume access to the complete training dataset, which is unrealistic in scenarios where the...

PrivTru: a Privacy-By-Design Data Trustee Minimizing Information Leakage

Data trustees serve as intermediaries that facilitate secure data sharing between independent parties. This paper offers a technical perspective on Data trustees, guided by privacy-by-design principles. We introduce PrivTru, an instantiation of a data trustee that provably achieves optimal privac...

Synthetic Tabular Data: Methods, Attacks and Defenses

Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much progress in synthetic data generation over the last decade, leveraging corresponding advances in machine learning an...

When Better Features Mean Greater Risks: the Performance-Privacy Trade-Off in Contrastive Learning

With the rapid advancement of deep learning technology, pre-trained encoder models have demonstrated exceptional feature extraction capabilities, playing a pivotal role in the research and application of deep learning. However, their widespread use has raised significant concerns about the risk o...

Breaking the Gaussian Barrier: Residual-PAC Privacy for Automatic Privatization

The Probably Approximately Correct PAC Privacy framework 1 provides a powerful instance-based methodology for certifying privacy in complex data-driven systems. However, existing PAC Privacy algorithms rely on a Gaussian mutual information upper bound. We show that this is in general too...

WordPress plugin WP Cookie Notice for GDPR, CCPA & ePrivacy Consent 跨站请求伪造漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation.WordPress is a blogging platform developed using the PHP language. The platform supports personal blog sites on PHP and MySQL servers.WordPress plugin is an application plugin. A cross-site request forgery vulnerability...

GeoClip: Geometry-Aware Clipping for Differentially Private SGD

Differentially private stochastic gradient descent DP-SGD is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping threshold, which significantly affects the trade-off between privac...

Mattermost Server 9.11.x < 9.11.13 / 10.5.x < 10.5.4 / 10.6.x < 10.6.3 / 10.7.1 Multiple Vulnerabilities (MMSA-2025-00458, MMSA-2025-00463, MMSA-2025-00467)

The version of Mattermost Server installed on the remote host is prior to 9.11.13, 10.5.4, 10.6.3, or 10.7.0. It is, therefore, affected by multiple vulnerabilities as referenced in the MMSA-2025-00458, MMSA-2025-00463, MMSA-2025-00467 advisories. - Mattermost versions 10.7.x = 10.7.0, 10.6.x =...

Weblate: exposure of personal IP address via email.

The exposure of personal IP addresses through email messages has been identified as a potential security issue. Email messages can pass through multiple servers, which may store or record the content, including the user's IP address, even if the email is encrypted during transit. The user's IP...

Popular Chrome Extensions Leak API Keys, User Data via HTTP and Hard-Coded Credentials

Cybersecurity researchers have flagged several popular Google Chrome extensions that have been found to transmit data in HTTP and hard-code secrets in their code, exposing users to privacy and security risks. "Several widely used extensions ... unintentionally transmit sensitive data over simple...

Pornhub, RedTube, and YouPorn block access in France, VPN use set to soar

VPNs Virtual Private Networks are suddenly popular in France. Not because France has suddenly become super privacy conscious, but because Pornhub, RedTube, and YouPorn, have blocked access in France. But why? Last year, France enacted a law mandating that pornographic sites implement stricter...

GHSA-FVX2-X7FF-FC56 Unauthenticated Disclosure of PSU HAX CMS Site Listings via haxPsuUsage API Endpoint

Summary An unauthenticated information disclosure vulnerability exists in the PSU deployment of HAX CMS via the haxPsuUsage API endpoint. This allows any remote unauthenticated user to retrieve a full list of PSU websites hosted on HAX CMS. When chained with other authorization issues e.g., HAX-3...

Network Hexagons under Attack: Secure Crowdsourcing of Geo-Referenced Data

A critical requirement for modern-day Intelligent Transportation Systems ITS is the ability to collect geo-referenced data from connected vehicles and mobile devices in a safe, secure and anonymous way. The Nexagon protocol, which builds on the IETF Locator/ID Separation Protocol LISP and the...

Inclusive, Differentially Private Federated Learning for Clinical Data

Federated Learning FL offers a promising approach for training clinical AI models without centralizing sensitive patient data. However, its real-world adoption is hindered by challenges related to privacy, resource constraints, and compliance. Existing Differential Privacy DP approaches often app...

Breaking Anonymity at Scale: Re-Identifying the Trajectories of 100K Real Users in Japan

Mobility traces represent a critical class of personal data, often subjected to privacy-preserving transformations before public release. In this study, we analyze the anonymized Yjmob100k dataset, which captures the trajectories of 100,000 users in Japan, and demonstrate how existing anonymizati...

Privacy Amplification through Synthetic Data: Insights from Linear Regression

Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this phenomenon, a rigorous theoretical understanding is stil...

FedShield-LLM: a Secure and Scalable Federated Fine-Tuned Large Language Model

Federated Learning FL offers a decentralized framework for training and fine-tuning Large Language Models LLMs by leveraging computational resources across organizations while keeping sensitive data on local devices. It addresses privacy and security concerns while navigating challenges associate...

Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents

The rise of Large Language Models LLMs has revolutionized Graphical User Interface GUI automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks ...