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...

Arbiter PUF: Uniqueness and Reliability Analysis Using Hybrid CMOS-Stanford Memristor Model

In an increasingly interconnected world, protecting electronic devices has grown more crucial because of the dangers of data extraction, reverse engineering, and hardware tampering. Producing chips in a third-party manufacturing company can let hackers change the design. As the Internet of Things...

Belkin F9K1122 安全漏洞

The Belkin F9K1122 is a WiFi signal extender. The Belkin F9K1122 suffers from a stack buffer overflow vulnerability that originates from the incorrect manipulation of the parameter L2TPUserName in the file /goform/formL2TPSetup, for which no detailed vulnerability details are provided at this tim...

Can Large Language Models Automate the Refinement of Cellular Network Specifications?

Cellular networks serve billions of users globally, yet concerns about reliability and security persist due to weaknesses in 3GPP standards. However, traditional analysis methods, including manual inspection and automated tools, struggle with increasingly expanding cellular network specifications...

CVE-2025-53109

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01...

CVE-2025-53110

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 0.6.4 o...

CVE-2025-34072

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol MCP Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embeddin...

When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-Box Setting

Watermarking has emerged as a promising solution to counter harmful or deceptive AI-generated content by embedding hidden identifiers that trace content origins. However, the robustness of current watermarking techniques is still largely unexplored, raising critical questions about their...

VLAI: a RoBERTa-Based Model for Automated Vulnerability Severity Classification

This paper presents VLAI, a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling fast...

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

The proliferation of Low-Rank Adaptation LoRA models has democratized personalized text-to-image generation, enabling users to share lightweight models e.g., personal portraits on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs c...

Model Context Protocol Python SDK 安全漏洞

Model Context Protocol Python SDK is a Model Context Protocol open source development tool for Model Context Protocol servers and clients. A security vulnerability exists in the Model Context Protocol Python SDK prior to version 1.9.4, which stems from an unhandled exception when handling malform...

Model Context Protocol Python SDK 安全漏洞

Model Context Protocol Python SDK is a Model Context Protocol open source development tool for Model Context Protocol servers and clients. A security vulnerability exists in the Model Context Protocol Python SDK prior to version 1.10.0, which stems from an uncaught ClosedResourceError that could...

We Urgently Need Privilege Management in MCP: a Measurement of API Usage in MCP Ecosystems

The Model Context Protocol MCP has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensibility and rich integrations, it also introduces a substantially expanded attack surface: any plugin can inherit broad...

SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a secure framework designed to prevent unauthorized editing in...

Cross-site Scripting (XSS)

Overview Affected versions of this package are vulnerable to Cross-site Scripting XSS via the shortdesc property, which is inserted into the DOM as raw HTML without proper escaping. An attacker can execute arbitrary JavaScript in the context of the user's browser by injecting malicious content...

Dependacy chain attack through hijacking broken github repository at https://github.com/huggingface/transformers/blob/main/src/\ntransformers/models/fuyu/\nconvert_fuyu_model_weights_to_hf.py

Description Type: Dependency Chain Attack through hijacking broken github repository Risk: High Allows arbitrary code execution in model conversion workflows Affected Asset: https://github.com/adept-ai-labs/adept-inference Broken URL in Hugging Face Transformers Root Cause The Hugging Face...

CVE-2025-53109

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01...

CVE-2025-53110

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 0.6.4 o...

Improper Neutralization of Input Used for LLM Prompting

Overview @modelcontextprotocol/server-slack is a MCP server for interacting with Slack Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the automatic link unfurling process. An attacker can access sensitive information by manipulating...

CVE-2025-53109 Model Context Protocol Servers Vulnerable to Path Validation Bypass via Prefix Matching and Symlink Handling

Model Context Protocol Servers is a collection of reference implementations for the model context protocol MCP. Versions of Filesystem prior to 0.6.4 or 2025.7.01 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 0.6.4 or 2025.7.01...