Membership Inference Attacks on Sequence Models

Sequence models, such as Large Language Models LLMs and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are insufficient to audit the resulting risks. We hypothesize that...

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...

Comprehensive Vulnerability Analysis Is Necessary for Trustworthy LLM-MAS

This paper argues that a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems LLM-MAS. These systems, which consist of multiple LLM-powered agents working collaboratively, are increasingly deployed in high-stakes applications bu...

SoK: Are Watermarks in LLMs Ready for Deployment?

Large Language Models LLMs have transformed natural language processing, demonstrating impressive capabilities across diverse tasks. However, deploying these models introduces critical risks related to intellectual property violations and potential misuse, particularly as adversaries can imitate...

On Automating Security Policies with Contemporary LLMs

The complexity of modern computing environments and the growing sophistication of cyber threats necessitate a more robust, adaptive, and automated approach to security enforcement. In this paper, we present a framework leveraging large language models LLMs for automating attack mitigation policy...

SQL Injection

Overview Affected versions of this package are vulnerable to SQL Injection via the QuerySubscribers function. An attacker can escalate privileges by injecting malicious SQL commands. Remediation Upgrade github.com/knadh/listmonk/models to version 5.0.0 or higher. References - GitHub Commit - POC...

QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality

This paper introduces QA-HFL, a quality-aware hierarchical federated learning framework that efficiently handles heterogeneous image quality across resource-constrained mobile devices. Our approach trains specialized local models for different image quality levels and aggregates their features...

VLMs Can Aggregate Scattered Training Patches

Whitepaper called VLMs Can Aggregate Scattered Training Patches...

BitBypass: a New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

The inherent risk of generating harmful and unsafe content by Large Language Models LLMs, has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignme...

Differentially Private Distribution Release of Gaussian Mixture Models Via KL-Divergence Minimization

Gaussian Mixture Models GMMs are widely used statistical models for representing multi-modal data distributions, with numerous applications in data mining, pattern recognition, data simulation, and machine learning. However, recent research has shown that releasing GMM parameters poses significan...

SAMSUNG Exynos 安全漏洞

SAMSUNG Exynos is a family of processors from South Korean company Samsung SAMSUNG. A security vulnerability exists in SAMSUNG Exynos, which stems from a double release vulnerability in the mobile processor that could lead to elevation of privilege. The following products are affected: SAMSUNG...

SAMSUNG多款产品 安全漏洞

SAMSUNG Exynos and others are products of the South Korean company Samsung SAMSUNG.SAMSUNG Exynos is a series of SoC, Arm architecture based processors developed and produced by Samsung Mobile.SAMSUNG Exynos 1280 is a processor for mobile devices.SAMSUNG Exynos 2200 is a cell phone chip processor...

Sylva: Tailoring Personalized Adversarial Defense in Pre-Trained Models Via Collaborative Fine-Tuning

Whitepaper called Sylva: Tailoring Personalized Adversarial Defense In Pre-Trained Models Via Collaborative Fine-Tuning...

CVE-2025-5442

A vulnerability, which was classified as critical, has been found in Linksys RE6500, RE6250, RE6300, RE6350, RE7000 and RE9000 1.0.013.001/1.0.04.001/1.0.04.002/1.1.05.003/1.2.07.001. This issue affects the function RPpingGatewayByBBS of the file /goform/RPpingGatewayByBBS. The manipulation of th...

CVE-2025-5440

A vulnerability classified as critical has been found in Linksys RE6500, RE6250, RE6300, RE6350, RE7000 and RE9000 1.0.013.001/1.0.04.001/1.0.04.002/1.1.05.003/1.2.07.001. This affects the function NTP of the file /goform/NTP. The manipulation of the argument...

CVE-2025-5440

CVE-2025-5440 affects Linksys RE6500/RE6250/RE6300/RE6350/RE7000/RE9000 (firmware variants 1.0.013.001–1.2.07.001). The NTP endpoint at /goform/NTP accepts parameters manual_year_select/manual_month_select/manual_day_select/manual_hour_select/manual_min_select/manual_sec_select that enable OS com...

CVE-2025-5438 Linksys RE6500/RE6250/RE6300/RE6350/RE7000/RE9000 WPS command injection

A vulnerability was found in Linksys RE6500, RE6250, RE6300, RE6350, RE7000 and RE9000 1.0.013.001/1.0.04.001/1.0.04.002/1.1.05.003/1.2.07.001. It has been declared as critical. Affected by this vulnerability is the function WPS of the file /goform/WPS. The manipulation of the argument PIN leads ...

CVE-2025-5438

CVE-2025-5438 affects Linksys RE6500/RE6250/RE6300/RE6350/RE7000/RE9000 devices with firmware versions 1.0.013.001, 1.0.04.001/1.0.04.002, 1.1.05.003, and 1.2.07.001. The WPS function at /goform/WPS is vulnerable to command injection through manipulation of the PIN argument, and the attack can be...

Silence Is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-Based Talking-Head Generation

Advances in talking-head animation based on Latent Diffusion Models LDM enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence,...

Trojan Horse Hunt in Time Series Forecasting for Space Operations

This competition hosted on Kaggle https://www.kaggle.com/competitions/trojan-horse-hunt-in-space is the first part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Applications" project funded by the European Space Agency...