Moneros Decentralized P2P Exchanges: Functionality, Adoption, and Privacy Risks

Privacy-focused cryptocurrencies like Monero remain popular, despite increasing regulatory scrutiny that has led to their delisting from major centralized exchanges. The latter also explains the recent popularity of decentralized exchanges DEXs with no centralized ownership structures. These...

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-Modal Retrieval-Augmented Generation

Multimodal Retrieval-Augmented Generation MRAG systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities. While text-based RAG privacy risks have been studied, multimodal data presents unique challenges. We provide the first systematic...

Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime

Training data reconstruction attacks enable adversaries to recover portions of a released model's training data. We consider the attacks where a reconstructor neural network learns to invert the random mapping between training data and model weights. Prior work has shown that an informed adversar...

A week in security (May 12 – May 18)

Last week on Malwarebytes Labs: Data broker protection rule quietly withdrawn by CFPB Meta sent cease and desist letter over AI training Google to pay $1.38 billion over privacy violations Android users bombarded with unskippable ads Last week on ThreatDown: ThreatDown introduces Firewall...

DynaNoise: Dynamic Probabilistic Noise Injection for Defending against Membership Inference Attacks

Membership Inference Attacks MIAs pose a significant risk to the privacy of training datasets by exploiting subtle differences in model outputs to determine whether a particular data sample was used during training. These attacks can compromise sensitive information, especially in domains such as...

Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy

Federated Learning with client-level differential privacy DP provides a promising framework for collaboratively training models while rigorously protecting clients' privacy. However, classic approaches like DP-FedAvg struggle when clients have heterogeneous privacy requirements, as they must...

WordPress plugin GDPR CCPA Compliance Support 安全漏洞

WordPress and WordPress plugin are both products of the WordPress Foundation. WordPress is a blogging platform developed in the PHP language. The platform supports personal blog sites on PHP and MySQL servers.WordPress plugin is an application plugin. A security vulnerability exists in WordPress...

Outsourced Privacy-Preserving Feature Selection Based on Fully Homomorphic Encryption

Feature selection is a technique that extracts a meaningful subset from a set of features in training data. When the training data is large-scale, appropriate feature selection enables the removal of redundant features, which can improve generalization performance, accelerate the training process...

Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs

In the age of cloud computing, data privacy protection has become a major challenge, especially when sharing sensitive data across cloud environments. However, how to optimize collaboration across cloud environments remains an unresolved problem. In this paper, we combine federated learning with...

Private Statistical Estimation Via Truncation

We introduce a novel framework for differentially private DP statistical estimation via data truncation, addressing a key challenge in DP estimation when the data support is unbounded. Traditional approaches rely on problem-specific sensitivity analysis, limiting their applicability. By leveragin...

CVE-2025-48219

O2 UK before 2025-05-19 allows subscribers to determine the Cell ID of other subscribers by initiating an IMS IP Multimedia Subsystem call and then reading the utran-cell-id-3gpp field of a Cellular-Network-Info SIP header, aka an ECI E-UTRAN Cell Identity leak. The Cell ID might be usable to...

PoLO: Proof-Of-Learning and Proof-Of-Ownership at Once with Chained Watermarking

Machine learning models are increasingly shared and outsourced, raising requirements of verifying training effort Proof-of-Learning, PoL to ensure claimed performance and establishing ownership Proof-of-Ownership, PoO for transactions. When models are trained by untrusted parties, PoL and PoO mus...

Automated Profile Inference with Language Model Agents

Impressive progress has been made in automated problem-solving by the collaboration of large language models LLMs based agents. However, these automated capabilities also open avenues for malicious applications. In this paper, we study a new threat that LLMs pose to online pseudonymity, called...

ACU: Analytic Continual Unlearning for Efficient and Exact Forgetting with Privacy Preservation

The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning CL to adapt to open-world environments. To meet privacy and security requirements, Continual Unlearning CU emerges as an important problem, aiming to sequentially forget particular...

Exploit for Out-of-bounds Write in Apple Macos

CVE-2025-31200 & CVE-2025-31201 | iMessage Zero-Click RCE Chai...

Privacy-Preserving AI for Encrypted Medical Imaging: a Framework for Secure Diagnosis and Learning

The rapid integration of Artificial Intelligence AI into medical diagnostics has raised pressing concerns about patient privacy, especially when sensitive imaging data must be transferred, stored, or processed. In this paper, we propose a novel framework for privacy-preserving diagnostic inferenc...

Proof-Of-Social-Capital: Privacy-Preserving Consensus Protocol Replacing Stake for Social Capital

Consensus protocols used today in blockchains often rely on computational power or financial stakes - scarce resources. We propose a novel protocol using social capital - trust and influence from social interactions - as a non-transferable staking mechanism to ensure fairness and decentralization...

On Membership Inference Attacks in Knowledge Distillation

Nowadays, Large Language Models LLMs are trained on huge datasets, some including sensitive information. This poses a serious privacy concern because privacy attacks such as Membership Inference Attacks MIAs may detect this sensitive information. While knowledge distillation compresses LLMs into...

Meta sent cease and desist letter over AI training

EU privacy advocacy group NOYB has clapped back at Meta over its plans to start training its AI model on European users' data. In a cease and desist letter to the social networking giant's Irish operation signed by founder Max Schrems, the non-profit demanded that it justify its actions or risk...

CVE-2025-47930

Zulip is an open-source team chat application. Starting in version 10.0 and prior to version 10.3, the "Who can create public channels" access control mechanism can be circumvented by creating a private or web-public channel, and then changing the channel privacy to public. A similar technique...