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...

Number withdrawn

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 This CVE number has been withdrawn...

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 ChuanhuChatGPT suffers from a path traversal vulnerability that stems from the use of an outdated gradio component that is susceptible to path traversal attacks...

ChuanhuChatGPT Information Disclosure Vulnerability

ChuanhuChatGPT provides a fast and easy-to-use Web GUI for ChatGPT/ChatGLM/LLaMA/StableLM/MOSS and other LLMs. ChuanhuChatGPT suffers from an information disclosure vulnerability that stems from a timing attack vulnerability in the password comparison logic...

Lunary security vulnerabilities

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...

Lunary security vulnerabilities

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...

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...

Ollama Reverse DNS Rebinding

The vulnerability of Ollama’s system for running and managing large language models is related to the use of reverse DNS resolution for IP addresses. Exploiting this vulnerability could allow a remote attacker to perform a DNS Rebinding attack or cause a service failure...

MAI-2024-0055

Large Vision Language Models LVLMs are susceptible to a sophisticated attack known as the bi-modal adversarial prompt BAP. This attack exploits the integration of textual and visual prompts to circumvent established safety protocols, thereby eliciting harmful outputs from models engineered to...

Number withdrawal

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 This CVE number has been withdrawn...

MAI-2024-0056

This vulnerability pertains to multimodal large language models MLLMs, where attackers can efficiently perform jailbreaking attacks by utilizing visual inputs to circumvent established safety protocols. The attack methodology involves integrating a visual module into the target LLM, followed by...

Getting Started with LLMs: Managing Data Collection

...

Number withdrawal

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 This CVE number has been withdrawn...

Number withdrawal

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 This CVE number has been withdrawn...

MAI-2024-0065

The ImgTrojan attack represents a sophisticated data poisoning strategy targeting Vision-Language Models VLMs. This method enables adversaries to circumvent built-in safety protocols by introducing a minimal number of maliciously designed image-caption pairs into the training dataset. These...

Three Tips to Protect Your Secrets from AI Accidents

Last year, the Open Worldwide Application Security Project OWASP published multiple versions of the "OWASP Top 10 For Large Language Models," reaching a 1.0 document in August and a 1.1 document in October. These documents not only demonstrate the rapidly evolving nature of Large Language Models,...

Teaching LLMs to Be Deceptive

Interesting research: "Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training": Abstract: Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given th...

MAI-2024-0059

Multimodal Large Language Models MLLMs operating within multi-agent environments are susceptible to a sophisticated attack known as "infectious jailbreak." This vulnerability is triggered by the introduction of a single adversarial image into the memory of one agent, which can rapidly propagate...

Chatbots and Human Conversation

For most of history, communicating with a computer has not been like communicating with a person. In their earliest years, computers required carefully constructed instructions, delivered through punch cards; then came a command-line interface, followed by menus and options and text boxes. If you...

AI likely to boost ransomware, warns government body

The British National Cyber Security Centre NCSC says it expects Artificial Intelligence AI to heighten the global ransomware threat. In a report, the NCSC makes the assessment that AI will almost certainly increase the volume and heighten the impact of cyberattacks over the next two years. We’re...