FedP3E: Privacy-Preserving Prototype Exchange for Non-IID IoT Malware Detection in Cross-Silo Federated Learning

As IoT ecosystems continue to expand across critical sectors, they have become prominent targets for increasingly sophisticated and large-scale malware attacks. The evolving threat landscape, combined with the sensitive nature of IoT-generated data, demands detection frameworks that are both...

No thanks: Google lets its Gemini AI access your apps, including messages [updated]

If you're an Android user, you'll need to take action if you don’t want Google's Gemini AI to have access to your apps. That's because, regardless of your previous settings, Google now allows Gemini to interact with third-party apps. Through Gemini extensions, it already had the ability to...

The vulnerability of the formWanTcpipSetup() function (/goform/formWanTcpipSetup) in the Belkin F9K1122 Wi-Fi range extender software allows a hacker to cause a service failure.

The vulnerability of the formWanTcpipSetup function /goform/formWanTcpipSetup of the Belkin F9K1122 Wi-Fi range extender software is due to a buffer overflow in the stack. Exploiting this vulnerability could allow an attacker to compromise privacy, the integrity of protected information, and caus...

The Impact of Event Data Partitioning on Privacy-Aware Process Discovery

Information systems support the execution of business processes. The event logs of these executions generally contain sensitive information about customers, patients, and employees. The corresponding privacy challenges can be addressed by anonymizing the event logs while still retaining utility f...

LDP$^3$: an Extensible and Multi-Threaded Toolkit for Local Differential Privacy Protocols and Post-Processing Methods

Local differential privacy LDP has become a prominent notion for privacy-preserving data collection. While numerous LDP protocols and post-processing PP methods have been developed, selecting an optimal combination under different privacy budgets and datasets remains a challenge. Moreover, the la...

Post-Processing in Local Differential Privacy: an Extensive Evaluation and Benchmark Platform

Local differential privacy LDP has recently gained prominence as a powerful paradigm for collecting and analyzing sensitive data from users' devices. However, the inherent perturbation added by LDP protocols reduces the utility of the collected data. To mitigate this issue, several post-processin...

webkitgtk: track sensitive user information

A flaw was found in WebKitGTK, which exists due to a logic issue in WebKit related to a user's privacy. A remote attacker may be able to track sensitive user information...

Cascade: Token-Sharded Private LLM Inference

As LLMs continue to increase in parameter size, the computational resources required to run them are available to fewer parties. Therefore, third-party inference services -- where LLMs are hosted by third parties with significant computational resources -- are becoming increasingly popular...

DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective

The widespread application of Deep Learning across diverse domains hinges critically on the quality and composition of training datasets. However, the common lack of disclosure regarding their usage raises significant privacy and copyright concerns. Dataset auditing techniques, which aim to...

Efficient Unlearning with Privacy Guarantees

Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning ML models trained on them. Machine unlearning has emerged as a practical means to facilitate model forgetting of data...

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation

Large Language Models LLMs have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks, and the boundary between learning and memorization. Addressi...

PROTEAN: Federated Intrusion Detection in Non-IID Environments through Prototype-Based Knowledge Sharing

In distributed networks, participants often face diverse and fast-evolving cyberattacks. This makes techniques based on Federated Learning FL a promising mitigation strategy. By only exchanging model updates, FL participants can collaboratively build detection models without revealing sensitive...

Layered, Overlapping, and Inconsistent: a Large-Scale Analysis of the Multiple Privacy Policies and Controls of U.S. Banks

Whitepaper called Layered, Overlapping, And Inconsistent: A Large-Scale Analysis Of The Multiple Privacy Policies And Controls Of U.S. Banks...

SoK: a Systematic Review of Context- and Behavior-Aware Adaptive Authentication in Mobile Environments

As mobile computing becomes central to digital interaction, researchers have turned their attention to adaptive authentication for its real-time, context- and behavior-aware verification capabilities. However, many implementations remain fragmented, inconsistently apply intelligent techniques, an...

Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models

Large language models LLMs have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual LLM developed by Meta. By querying the model with carefully...

UniAud: a Unified Auditing Framework for High Auditing Power and Utility with One Training Run

Differentially private DP optimization has been widely adopted as a standard approach to provide rigorous privacy guarantees for training datasets. DP auditing verifies whether a model trained with DP optimization satisfies its claimed privacy level by estimating empirical privacy lower bounds...

Taiwan NSB Alerts Public on Data Risks from Douyin, Weibo, and RedNote Over China Ties

Taiwan's National Security Bureau NSB has warned that China-developed applications like RedNote aka Xiaohongshu, Weibo, Douyin, WeChat, and Baidu Cloud pose security risks due to excessive data collection and data transfer to China. The alert comes following an inspection of these apps carried ou...

Human-Centered Interactive Anonymization for Privacy-Preserving Machine Learning: a Case for Human-Guided K-Anonymity

Privacy-preserving machine learning ML seeks to balance data utility and privacy, especially as regulations like the GDPR mandate the anonymization of personal data for ML applications. Conventional anonymization approaches often reduce data utility due to indiscriminate generalization or...

SUSE CVE-2025-3913

Mattermost versions 10.7.x = 10.7.0, 10.6.x = 10.6.2, 10.5.x = 10.5.3, 9.11.x = 9.11.12 fail to properly validate permissions when changing team privacy settings, allowing team administrators without the 'invite user' permission to access and modify team invite IDs via the...

SUSE-SU-2025:20465-1 Security update for gpg2

This update for gpg2 fixes the following issues: - gpg: Allow the use of an ADSK subkey as ADSK subkey. bsc1239119 CVE-2025-30258 - Don't install expired sks certificate bsc1243069...