Computational Attestations of Polynomial Integrity Towards Verifiable Machine-Learning

Machine-learning systems continue to advance at a rapid pace, demonstrating remarkable utility in various fields and disciplines. As these systems continue to grow in size and complexity, a nascent industry is emerging which aims to bring machine-learning-as-a-service MLaaS to market. Outsourcing...

PYSEC-2025-221

vantage6 is an open-source infrastructure for privacy preserving analysis. The JWT secret key in the vantage6 server is auto-generated unless defined by the user. The auto-generated key is a UUID1, which is not cryptographically secure as it is predictable to some extent. This vulnerability is...

CVE-2025-43863

vantage6 contains a brute-force vulnerability in the change password flow when an attacker has an authenticated session. The issue arises from unlimited password-change attempts via the route, enabling password-guessing and account compromise. Multiple sources (CVEs, advisories, and vendor notes)...

US Tops List of Unsecured Cameras Exposing Homes and Offices

A BitSight report reveals over 40,000 internet-connected security cameras globally are exposed, streaming live footage without protection. Learn how common devices, from home cameras to factory surveillance, pose privacy and security risks and get simple tips to secure your own...

User Perceptions and Attitudes toward Untraceability in Messaging Platforms

Mainstream messaging platforms offer a variety of features designed to enhance user privacy, such as disappearing messages, password-protected chats, and end-to-end encryption E2EE, which primarily protect message contents. Beyond contents, the transmission of messages generates metadata that can...

PT-2025-25341 · Vantage6 · Vantage6

Name of the Vulnerable Software and Affected Versions: vantage6 versions prior to 4.11 Description: The issue concerns an open-source framework designed for privacy-enhancing technologies such as Federated Learning and Multi-Party Computation. If an attacker gains access to an authenticated...

Byzantine Outside, Curious Inside: Reconstructing Data through Malicious Updates

Federated learning FL enables decentralized machine learning without sharing raw data, allowing multiple clients to collaboratively learn a global model. However, studies reveal that privacy leakage is possible under commonly adopted FL protocols. In particular, a server with access to client...

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR

Extended reality XR systems, which consist of virtual reality VR, augmented reality AR, and mixed reality XR, offer a transformative interface for immersive, multi-modal, and embodied human-computer interaction. In this paper, we envision that multi-modal multi-task M3T federated foundation model...

TimberStrike: Dataset Reconstruction Attack Revealing Privacy Leakage in Federated Tree-Based Systems

Federated Learning has emerged as a privacy-oriented alternative to centralized Machine Learning, enabling collaborative model training without direct data sharing. While extensively studied for neural networks, the security and privacy implications of tree-based models remain underexplored. This...

Single Block On

In the digital age, individuals increasingly maintain active presences across multiple platforms ranging from social media and messaging applications to professional and communication tools. However, the current model for managing user level privacy and abuse is siloed, requiring users to block...

vantage6 安全漏洞

vantage6 is a vantage6 open source priVAcy preserviNg federalTed leArningG infrastructure for Secure Insight eXchange. A security vulnerability exists in vantage6 versions prior to 4.11 that stems from the change password feature allowing unlimited attempts, which could lead to a brute force atta...

Differentially Private Relational Learning with Entity-Level Privacy Guarantees

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy DP offers a principled approach for quantifying privacy risks, with DP-SGD emerging as a standard mechanism for...

23andMe raked by Congress on privacy, sale of genetic data

In a Senate hearing adequately titled “23 and You: The Privacy and National Security Implications of the 23andMe Bankruptcy,” 23andMe executives addressed concerns about the privacy implications of the company’s sale and the handling of associated genetic data. For those who missed the latest...

LLMail-Inject: a Dataset from a Realistic Adaptive Prompt Injection Challenge

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models LLMs to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks ca...

Differentially Private Federated $K$-Means Clustering with Server-Side Data

Clustering is a cornerstone of data analysis that is particularly suited to identifying coherent subgroups or substructures in unlabeled data, as are generated continuously in large amounts these days. However, in many cases traditional clustering methods are not applicable, because data are...

TRIDENT -- a Three-Tier Privacy-Preserving Propaganda Detection Model in Mobile Networks Using Transformers, Adversarial Learning, and Differential Privacy

The proliferation of propaganda on mobile platforms raises critical concerns around detection accuracy and user privacy. To address this, we propose TRIDENT - a three-tier propaganda detection model implementing transformers, adversarial learning, and differential privacy which integrates syntact...

DiffUMI: Training-Free Universal Model Inversion Via Unconditional Diffusion for Face Recognition

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which are traditionally viewed as privacy-preserving. However, model inversion...

Digital Privacy Everywhere

The increasing proliferation of digital and mobile devices equipped with cameras, microphones, GPS, and other privacy invasive components has raised significant concerns for businesses operating in sensitive or policy restricted environments. Current solutions rely on passive enforcement, such as...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

Devil'S Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols

Graph neural networks GNNs have achieved significant success in graph representation learning and have been applied to various domains. However, many real-world graphs contain sensitive personal information, such as user profiles in social networks, raising serious privacy concerns when graph...