CVE-2025-67509: Improper Control of Generation of Code

Neuron is a PHP framework for creating and orchestrating AI Agents. Versions 2.8.11 and below use MySQLSelectTool, which is vulnerable to Read-Only Bypass. MySQLSelectTool is intended to be a read-only SQL tool e.g., for LLM agent querying, however, validation based on the first keyword e.g.,...

Execution with Unnecessary Privileges

Overview neuron-core/neuron-ai is a The PHP Agentic Framework. Affected versions of this package are vulnerable to Execution with Unnecessary Privileges via the MySQLWriteTool which us PDO::prepare + execute without semantic restrictions. An attacker can execute arbitrary and potentially...

Arbitrary Code Injection

Overview neuron-core/neuron-ai is a The PHP Agentic Framework. Affected versions of this package are vulnerable to Arbitrary Code Injection via the validation based on the first keyword e.g., SELECT and a forbidden-keyword list does not block file-writing constructs such in the MySQLSelectTool. A...

LLM Causality Analysis Framework

A comprehensive framework for multi-level causality analysis in Large Language Models LLMs, enabling systematic investigation of safety mechanisms and misbehavior detection across token, neuron, layer, and representation levels. Includes the whitepaper 2512.04841.pdf titled SoK: A Comprehensive...

EUVD-2007-5031

Malware in sbrugna...

EUVD-2007-6507

Malware in sbrugna...

EUVD-2006-6975

Malware in sbrugna...

EUVD-2019-14631

Malware in sbrugna...

EUVD-2006-1899

Malware in sbrugna...

EUVD-2007-4354

Malware in sbrugna...

EUVD-2007-6506

Malware in sbrugna...

EUVD-2024-33368

Malicious code in bioql PyPI...

EUVD-2024-33367

Malicious code in bioql PyPI...

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

In deployment and application, large language models LLMs typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety mechanisms with adversarial prompts, has placed increasing pressure ...

NCCR: to Evaluate the Robustness of Neural Networks and Adversarial Examples

Neural networks have received a lot of attention recently, and related security issues have come with it. Many studies have shown that neural networks are vulnerable to adversarial examples that have been artificially perturbed with modification, which is too small to be distinguishable by human...

Safeguarding Federated Learning-Based Road Condition Classification

Federated Learning FL has emerged as a promising solution for privacy-preserving autonomous driving, specifically camera-based Road Condition Classification RCC systems, harnessing distributed sensing, computing, and communication resources on board vehicles without sharing sensitive image data...

SECNEURON: Reliable and Flexible Abuse Control in Local LLMs Via Hybrid Neuron Encryption

Large language models LLMs with diverse capabilities are increasingly being deployed in local environments, presenting significant security and controllability challenges. These locally deployed LLMs operate outside the direct control of developers, rendering them more susceptible to abuse...

CVE-2024-10965

A vulnerability classified as problematic was found in emqx neuron up to 2.10.0. Affected by this vulnerability is an unknown functionality of the file /api/v2/schema of the component JSON File Handler. The manipulation leads to information disclosure. The attack can be launched remotely. The pat...

CVE-2024-10964

A vulnerability classified as critical has been found in emqx neuron up to 2.10.0. Affected is the function handleaddplugin in the library cmd.library of the file plugins/restful/pluginhandle.c. The manipulation leads to buffer overflow. It is possible to launch the attack remotely. It is...

CVE-2024-10965

A vulnerability classified as problematic was found in emqx neuron up to 2.10.0. Affected by this vulnerability is an unknown functionality of the file /api/v2/schema of the component JSON File Handler. The manipulation leads to information disclosure. The attack can be launched remotely. The pat...