MAI-2024-0003

Large Language Models LLMs are susceptible to the "SequentialBreak" jailbreak attack, wherein a malicious prompt is embedded within a sequence of benign prompts in a single query. This technique exploits the LLM's attention mechanism, which prioritizes benign prompts, thereby allowing the harmful...

MAI-2024-0012

Large Vision-Language Models VLMs are susceptible to a sophisticated black-box jailbreak attack known as IDEATOR. This attack utilizes a separate VLM to craft malicious image-text pairs designed to circumvent the target VLM's safety protocols. By iteratively refining prompts based on the target...

MAI-2024-0035

This vulnerability affects various Large Vision-Language Models LVLMs, wherein ostensibly safe images, when combined with additional safe images and specific prompts, can be exploited to produce unsafe and harmful content. The attack methodology, known as the Safety Snowball Agent, leverages the...

Researchers Reveal 'Deceptive Delight' Method to Jailbreak AI Models

Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models LLMs during the course of an interactive conversation by sneaking in an undesirable instruction between benign ones. The approach has been codenamed Deceptive Delight by...

A Single Cloud Compromise Can Feed an Army of AI Sex Bots

Organizations that get relieved of credentials to their cloud environments can quickly find themselves part of a disturbing new trend: Cybercriminals using stolen cloud credentials to operate and resell sexualized AI-powered chat services. Researchers say these illicit chat bots, which use custom...

Supercharging Your AI Applications with Spring AI Advisors

In the rapidly evolving world of artificial intelligence, developers are constantly seeking ways to enhance their AI applications. Spring AI, a Java framework for building AI-powered applications, has introduced a powerful feature: the Spring AI Advisors. The advisors can supercharge your AI...

MAI-2024-0023

The multi-round jailbreak attack targets Large Language Models LLMs by exploiting their iterative prompt-response mechanisms to bypass established safety protocols. This attack method involves progressively refining prompts over multiple interactions, thereby inducing the LLM to produce unintende...

AI Meets Spring Petclinic: Implementing an AI Assistant with Spring AI (Part II)

Recap of Part I In the first part of this blog series, we explored the basics of integrating Spring AI with large language models. We walked through building a custom ChatClient, leveraging Function Calling for dynamic interactions, and refining our prompts to suit the Spring Petclinic use case. ...

AI Meets Spring Petclinic: Implementing an AI Assistant with Spring AI (Part I)

Introduction In this two-parts blog post, I will discuss the modifications I made to Spring Petclinic to incorporate an AI assistant that allows users to interact with the application using natural language. Introduction to Spring Petclinic Spring Petclinic serves as the primary reference...

MAI-2024-0006

Large Language Models LLMs are susceptible to a sophisticated multi-turn jailbreaking attack known as the "RED QUEEN ATTACK." This technique involves engaging the LLM in a series of conversational exchanges that obscure malicious intent by portraying the user as a protector aiming to prevent...

Flowise 安全漏洞

Flowise is a FlowiseAI open source tool for easily building LLM applications. A security vulnerability exists in Flowise version 1.8.2, which results in a denial of service due to improper handling of user-supplied input to the "/api/v1/get-upload-file" api endpoint...

Indirect prompt injection in the real world: how people manipulate neural networks

What is prompt injection? Large language models LLMs – the neural network algorithms that underpin ChatGPT and other popular chatbots – are becoming ever more powerful and inexpensive. For this reason, third-party applications that make use of them are also mushrooming, from systems for document...

Open WebUI 0.1.105 Persistent Cross Site Scripting Vulnerability

Title: Open WebUI Stored Cross-Site Scripting Publication URL: https://korelogic.com/Resources/Advisories/KL-001-2024-005.txt 1. Vulnerability Details Affected Vendor: Open WebUI Affected Product: Open WebUI Affected Version: 0.1.105 Platform: Debian 12 CWE Classification: CWE-79: Improper...

lunary 访问控制错误漏洞

lunary is lunary open source a production toolkit for LLM . An access control error vulnerability exists in lunary that stems from improper access control and can be exploited by an attacker to change the name of an organization...

Meta Pauses AI Training on EU User Data Amid Privacy Concerns

Meta on Friday said it's delaying its efforts to train the company's large language models LLMs using public content shared by adult users on Facebook and Instagram in the European Union following a request from the Irish Data Protection Commission DPC. The company expressed disappointment at...

Lunary 安全漏洞

Lunary is lunary open source a production toolkit for LLM. Lunary has an authorization issue vulnerability that stems from the lack of proper authorization checks in the dataset deletion end node, which can be exploited by an attacker to delete any dataset...

ChuanhuChatGPT Access Control Error Vulnerability

ChuanhuChatGPT is a lightweight and easy-to-use Web GUI for ChatGPT/ChatGLM/LLaMA/StableLM/MOSS and many other LLMs. ChuanhuChatGPT suffers from an access control error vulnerability that stems from an improper access control mechanism...

ChuanhuChatGPT Path Traversal Vulnerability

ChuanhuChatGPT provides a fast and easy-to-use Web GUI for ChatGPT/ChatGLM/LLaMA/StableLM/MOSS and other LLMs. ChuanhuChatGPT suffers from a path traversal vulnerability that stems from the use of an outdated gradio component that is susceptible to path traversal attacks...

Number withdrawn

Lunary is a production toolkit for LLMs from lunary open source. This CVE number has been withdrawn...

Lunary 安全漏洞

lunary is lunary open source a production toolkit for LLM . An improper access control vulnerability exists in lunary, which can be exploited by an attacker to update any organization user as the organization owner...