Automatic Red Teaming LLM-Based Agents with Model Context Protocol Tools

The remarkable capability of large language models LLMs has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol MCP tools have become the de facto standard and are now widely...

D-Link DIR-513 Buffer Overflow Vulnerability (CNVD-2025-23468)

D-Link DIR-513 is a wireless router product from China's AUO D-Link. The D-Link DIR-513 suffers from a buffer overflow vulnerability due to incorrect manipulation of the parameter webpage in the file /goform/formWPS, no details of the vulnerability are provided at this time...

PyTorch 安全漏洞

PyTorch is a Python package open-sourced by PyTorch. PyTorch= suffers from a buffer overflow vulnerability that stems from a boundary error in the PyTorch model compilation when handling untrusted input, which can be exploited by an attacker to cause a denial of service...

CVE-2025-57953

Improper Neutralization of Input During Web Page Generation 'Cross-site Scripting' vulnerability in 100plugins Open User Map open-user-map allows DOM-Based XSS.This issue affects Open User Map: from n/a through = 1.4.14...

MINI-4M32-M46X-6GGW

Bulletin has no description...

CVE-2025-23354

NVIDIA Megatron-LM for all platforms contains a vulnerability in the ensembleclassifer script where malicious data created by an attacker may cause an injection. A successful exploit of this vulnerability may lead to code execution, escalation of privileges, Information disclosure, and data...

CVE-2025-23353

NVIDIA Megatron-LM for all platforms contains a vulnerability in the msdp preprocessing script where malicious data created by an attacker may cause an injection. A successful exploit of this vulnerability may lead to code execution, escalation of privileges, Information disclosure, and data...

CVE-2025-23348

NVIDIA Megatron-LM for all platforms contains a vulnerability in the pretraingpt script, where malicious data created by an attacker may cause a code injection issue. A successful exploit of this vulnerability may lead to code execution, escalation of privileges, information disclosure, and data...

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation

Fine-tuning large language models LLMs with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific domains. Given the shared characteristics in data across different organizations, the idea of collaboratively fine-tuning an LLM using data from multiple...

This Is How Your LLM Gets Compromised

Poisoned data. Malicious LoRAs. Trojan model files. AI attacks are stealthier than ever—often invisible until it’s too late. Here’s how to catch them before they catch you...

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Retrieval-Augmented Generation RAG is an emerging approach in natural language processing that combines large language models LLMs with external document retrieval to produce more accurate and grounded responses. While RAG has shown strong potential in reducing hallucinations and improving factua...

The vulnerability of the /usr/sbin/goahead file in the microprogramming software for D-link DIR-823X allows a hacker to execute arbitrary commands.

The vulnerability of the /usr/sbin/goahead file in the microprogramming software for D-link DIR-823X routers is related to the failure to take measures to neutralize specific elements. Exploiting this vulnerability allows a remote attacker to execute arbitrary commands...

CVE-2025-9964

CVE-2025-9964 affects Novakon P series (P – V2001.A.C518o2). The root cause is an absent/no password for the root user, enabling physical attackers to access the console. CVSS shows a HIGH impact with physical attack vector and no user interaction. The issue is documented across multiple feeds (N...

Semantic-Aware Fuzzing: an Empirical Framework for LLM-Guided, Reasoning-Driven Input Mutation

Security vulnerabilities in Internet-of-Things devices, mobile platforms, and autonomous systems remain critical. Traditional mutation-based fuzzers -- while effectively explore code paths -- primarily perform byte- or bit-level edits without semantic reasoning. Coverage-guided tools such as AFL+...

Security Bulletin: NVIDIA Megatron LM - September 2025

NVIDIA has released a software update for NVIDIA® Megatron LM. To protect your system, clone or update this software to version 0.13.1 and 0.12.3 or later from NVIDIA/Megatron-LM on NVIDIA GitHub. Go to NVIDIA Product Security...

PT-2025-39165

Name of the Vulnerable Software and Affected Versions Novakon P series version P – V2001.A.C518o2 Description A default or missing password for the root user allows physical attackers to easily access the console. This impacts the Novakon P series devices. Recommendations Set a strong password fo...

AI-Powered App Exposes User Data, Creates Risk of Supply Chain Attacks

Trend™ Research’s analysis of Wondershare RepairIt reveals how the AI-driven app exposed sensitive user data due to unsecure cloud storage practices and hardcoded credentials, creating risks of model tampering and supply chain attacks...

FlowCrypt: Flow-Based Lightweight Encryption with Near-Lossless Recovery for Cloud Photo Privacy

The widespread adoption of smartphone photography has led users to increasingly rely on cloud storage for personal photo archiving and sharing, raising critical privacy concerns. Existing deep learning-based image encryption schemes, typically built upon CNNs or GANs, often depend on traditional...

Towards Adapting Federated and Quantum Machine Learning for Network Intrusion Detection: a Survey

This survey explores the integration of Federated Learning FL with Network Intrusion Detection Systems NIDS, with particular emphasis on deep learning and quantum machine learning approaches. FL enables collaborative model training across distributed devices while preserving data privacy-a critic...

CVE-2025-57637

Buffer overflow vulnerability in D-Link DI-7100G 2020-02-21 in the sub451754 function of the jhttpd service in the viav4 parameter allowing attackers to cause a denial of service or execute arbitrary code...