DualBreach: Efficient Dual-Jailbreaking Via Target-Driven Initialization and Multi-Target Optimization

Recent research has focused on exploring the vulnerabilities of Large Language Models LLMs, aiming to elicit harmful and/or sensitive content from LLMs. However, due to the insufficient research on dual-jailbreaking -- attacks targeting both LLMs and Guardrails, the effectiveness of existing...

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-Box Large Language Models

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to generate poisoned texts and improve the stealthiness,...

CVE-2025-43962

In LibRaw before 0.21.4, phaseonecorrect in decoders/loadmfbacks.cpp has out-of-bounds reads for tag 0x412 processing, related to large w0 or w1 values or the frac and mult calculations...

Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data

Differentially private DP machine learning often relies on the availability of public data for tasks like privacy-utility trade-off estimation, hyperparameter tuning, and pretraining. While public data assumptions may be reasonable in text and image domains, they are less likely to hold for tabul...

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content

Large Language Models LLM have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel approach focuses on a post-generation correction mechanism...

Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: a Railway Casestudy

Operational Technology Cybersecurity OTCS continues to be a dominant challenge for critical infrastructure such as railways. As these systems become increasingly vulnerable to malicious attacks due to digitalization, effective documentation and compliance processes are essential to protect these...

Everything You Wanted to Know about LLM-Based Vulnerability Detection but Were Afraid to Ask

Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities? Current evaluations, which...

Artificial Intelligence – What's all the fuss?

Talking about AI: Definitions Artificial Intelligence AI — AI refers to the simulation of human intelligence in machines, enabling them to perform tasks that typically require human intelligence, such as decision-making and problem-solving. AI is the broadest concept in this field, encompassing...

RabbitMQ 3.11.x < 3.11.24 / 3.12.x < 3.12.7 Denial of Service

The version of RabbitMQ installed on the remote host is 3.11.x prior to 3.11.24, or 3.12.x prior to 3.12.7. It is, therefore, affected by a denial of service vulnerability: - RabbitMQ is a multi-protocol messaging and streaming broker. HTTP API did not enforce an HTTP request body limit, making i...

DEBIAN-CVE-2025-22122

In the Linux kernel, the following vulnerability has been resolved: block: fix adding folio to bio 4GB folio is possible on some ARCHs, such as aarch64, 16GB hugepage is supported, then 'offset' of folio can't be held in 'unsigned int', cause warning in bioaddfolionofail and IO failure. Fix it by...

DEBIAN-CVE-2025-22091

In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix pagesize variable overflow Change all variables storing mlx5umemmkcfindbestpgsz result to unsigned long to support values larger than 31 and avoid overflow. For example: If we try to register 4GB of memory that is...

UBUNTU-CVE-2025-22091

In the Linux kernel, the following vulnerability has been resolved: RDMA/mlx5: Fix pagesize variable overflow Change all variables storing mlx5umemmkcfindbestpgsz result to unsigned long to support values larger than 31 and avoid overflow. For example: If we try to register 4GB of memory that is...

UBUNTU-CVE-2025-22122

In the Linux kernel, the following vulnerability has been resolved: block: fix adding folio to bio 4GB folio is possible on some ARCHs, such as aarch64, 16GB hugepage is supported, then 'offset' of folio can't be held in 'unsigned int', cause warning in bioaddfolionofail and IO failure. Fix it by...

Mattermost 安全漏洞

Mattermost is an open source collaboration platform from Mattermost, Inc. in the United States. Mattermost suffers from an information disclosure vulnerability. The vulnerability stems from an under-restricted LLM request domain. An attacker can exploit the vulnerability to perform prompt injecti...

Provable Secure Steganography Based on Adaptive Dynamic Sampling

The security of private communication is increasingly at risk due to widespread surveillance. Steganography, a technique for embedding secret messages within innocuous carriers, enables covert communication over monitored channels. Provably Secure Steganography PSS is state of the art for making...

OpDiffer: LLM-Assisted Opcode-Level Differential Testing of Ethereum Virtual Machine

As Ethereum continues to thrive, the Ethereum Virtual Machine EVM has become the cornerstone powering tens of millions of active smart contracts. Intuitively, security issues in EVMs could lead to inconsistent behaviors among smart contracts or even denial-of-service of the entire blockchain...

Linux kernel 安全漏洞

Linux kernel is the kernel used by Linux, the open source operating system of the Linux Foundation in the United States. A security vulnerability exists in the Linux kernel that stems from a possible overflow of the bioffset field when a large page is added to the bio at the block level...

A Scalable Framework for Post-Quantum Authentication in Public Key Infrastructures

This work explores the performance and scalability of a hierarchical certificate authority framework with automated certificate issuance employing post-quantum cryptographic PQC signature algorithms. The system is designed for compatibility with both classical and PQC algorithms, promoting...

UBUNTU-CVE-2025-3277

An integer overflow can be triggered in SQLite’s concatws function. The resulting, truncated integer is then used to allocate a buffer. When SQLite then writes the resulting string to the buffer, it uses the original, untruncated size and thus a wild Heap Buffer overflow of size 4GB can be...

Prompt Engineering Techniques with Spring AI

This blog post demonstrates practical implementations of Prompt Engineering techniques using Spring AI. The examples and patterns in this article are based on the comprehensive Prompt Engineering Guide that covers the theory, principles, and patterns of effective prompt engineering. The blog show...