AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...

Automated Static Vulnerability Detection Via a Holistic Neuro-Symbolic Approach

Static vulnerability detection is still a challenging problem and demands excessive human efforts, e.g., manual curation of good vulnerability patterns. None of prior works, including classic program analysis or Large Language Model LLM-based approaches, have fully automated such vulnerability...

CVE-2025-28029

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a buffer overflow vulnerability in cstecgi.cgi...

CVE-2025-28026

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a buffer overflow vulnerability in downloadFile.cgi...

CVE-2025-28032

TOTOLINK A800R V4.1.2cu.5137B20200730, A810R V4.1.2cu.5182B20201026, A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 contain a pre-auth buffer overflow vulnerability in the setNoticeCfg function through the IpForm paramet...

TOTOLINK多款产品 安全漏洞

TOTOLINK A3000RU and others are products of China-based TOTOLINK Electronics TOTOLINK.TOTOLINK A3000RU is a wireless router.TOTOLINK A950RG is an Ultra-Generation Giga wireless router.TOTOLINK A830R is a wireless dual-band router. A security vulnerability exists in several TOTOLINK products, whic...

[SECURITY] Fedora 42 Update: llama-cpp-b4094-11.fc42

The main goal of llama.cpp is to run the LLaMA model using 4-bit integer quantization on a MacBook Plain C/C++ implementation without dependencies Apple silicon first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks AVX, AVX2 and AVX512 support for x86 architectures Mixed F...

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,...

Towards Model Resistant to Transferable Adversarial Examples Via Trigger Activation

Whitepaper called Towards Model Resistant To Transferable Adversarial Examples Via Trigger Activation...

What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale

Diffusion models DMs have revolutionized text-to-image generation, enabling the creation of highly realistic and customized images from text prompts. With the rise of parameter-efficient fine-tuning PEFT techniques like LoRA, users can now customize powerful pre-trained models using minimal...

REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-To-Image Diffusion Models

The rapid advancement of generative AI highlights the importance of text-to-image T2I security, particularly with the threat of backdoor poisoning. Timely disclosure and mitigation of security vulnerabilities in T2I models are crucial for ensuring the safe deployment of generative models. We...

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...

CVE-2025-32434

PyTorch is a Python package that provides tensor computation with strong GPU acceleration and deep neural networks built on a tape-based autograd system. In version 2.5.1 and prior, a Remote Command Execution RCE vulnerability exists in PyTorch when loading a model using torch.load with...

DEBIAN-CVE-2025-32434

PyTorch is a Python package that provides tensor computation with strong GPU acceleration and deep neural networks built on a tape-based autograd system. In version 2.5.1 and prior, a Remote Command Execution RCE vulnerability exists in PyTorch when loading a model using torch.load with...

CVE-2025-32434 PyTorch: `torch.load` with `weights_only=True` leads to remote code execution

PyTorch is a Python package that provides tensor computation with strong GPU acceleration and deep neural networks built on a tape-based autograd system. In version 2.5.1 and prior, a Remote Command Execution RCE vulnerability exists in PyTorch when loading a model using torch.load with...

CVE-2025-32434 PyTorch: `torch.load` with `weights_only=True` leads to remote code execution

PyTorch is a Python package that provides tensor computation with strong GPU acceleration and deep neural networks built on a tape-based autograd system. In version 2.5.1 and prior, a Remote Command Execution RCE vulnerability exists in PyTorch when loading a model using torch.load with...

Designing a Reliable Lateral Movement Detector Using a Graph Foundation Model

Foundation models have recently emerged as a new paradigm in machine learning ML. These models are pre-trained on large and diverse datasets and can subsequently be applied to various downstream tasks with little or no retraining. This allows people without advanced ML expertise to build ML...

Towards Explainable and Lightweight AI for Real-Time Cyber Threat Hunting in Edge Networks

As cyber threats continue to evolve, securing edge networks has become increasingly challenging due to their distributed nature and resource limitations. Many AI-driven threat detection systems rely on complex deep learning models, which, despite their high accuracy, suffer from two major...

Q-FAKER: Query-Free Hard Black-Box Attack Via Controlled Generation

Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even black-box attack methods also require the target model's output information. They are not applicable in real-world...