617 matches found
ai-captcha-bypass
AI-Powered CAPTCHA Solver This project is a Python-based command-line tool that uses large multimodal models LMMs like OpenAI's GPT-4o and Google's Gemini to automatically solve various types of CAPTCHAs. It leverages Selenium for web browser automation to interact with web pages and solve CAPTCH...
hcaptcha-challenger
hCaptcha Challenger 🚀 Gracefully face hCaptcha challenge with multimodal large language model. Introduction Does not rely on any Tampermonkey script. Does not use any third-party anti-captcha services. Just implement some interfaces to make AI vs AI possible. Documentation: English | 简体中文 | Русск...
Multimodal-Unlearnable-Examples
Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning ACM MM2024 Abstract : Multimodal contrastive learning MCL has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this...
Learning-to-Detect
Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models Official implementation of “Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models.” This repository contains the data-processing, hidden-state extraction, classifier training, safety-pattern...
ContextHound
ContextHound Static analysis tool that scans your codebase for LLM prompt-injection and multimodal security vulnerabilities. Runs offline, no API calls required. The ContextHound ecosystem ContextHound is available across your entire development and browsing workflow: Tool| What it does| Install...
Multimodal-web-attack-Dataset
MWAD: A Multimodal Web Attack Dataset for AI-Driven SQL Injection Detection Overview The Multimodal Web Attack Dataset MWAD is a novel labelled cybersecurity dataset developed as part of the author's research in cybersecurity at La Trobe University, Australia. The dataset generation methodology,...
bordair-multimodal
Multimodal Prompt Injection Dataset 516,588 labeled samples 251,782 attack + 251,576 benign, plus a 13,230-sample real-world validation split across five dataset versions plus external dataset ingestion, covering cross-modal, multi-turn, adversarial suffix, jailbreak template, indirect injection,...
EXPLOIT-CVE-2026-22778
CVE-2026-22778 — vLLM RCE in video processing Vulnerable lab + proof of concept for CVE-2026-22778 CVSS 9.8, an unauthenticated remote code execution chain in vLLM's multimodal ingestion path. | ---|--- CVE| CVE-2026-22778 Advisory| GHSA-4r2x-xpjr-7cvv Affected| vLLM = 0.8.3, vLLM turned...
vLLM 0.8.3 - 0.14.0 - Information Disclosure
vLLM 0.8.3 to - 0.14.1 contains an information disclosure caused by leaking a heap address in error messages from the multimodal endpoint when processing invalid images, letting remote attackers reduce ASLR entropy, exploit requires sending invalid images. id: CVE-2026-22778 info: name: vLLM 0.8....
CVE-2026-126397
The vLLM library versions 0.10.1 through 0.31.0 are vulnerable to a Denial of Service (DoS) attack affecting Cohere2 Vision models. The root cause is the lack of a server-side upper bound on the mm_processor_kwargs.max_patches value, which is forwarded directly from request-controlled inputs to t...
CVE-2026-126397 vLLM 0.10.1 before 0.31.0 Cohere2 Vision DoS via max_patches
vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mmprocessorkwargs.maxpatches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completio...
EUVD-2026-125168
vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mmprocessorkwargs.maxpatches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completio...
PT-2026-146683
Name of the Vulnerable Software and Affected Versions vLLM versions 0.10.1 through 0.30.9 Description An issue exists where the software forwards a request-controlled mm processor kwargs.max patches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound...
CVE-2026-100962
NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might cause information disclosure...
CVE-2026-100962
The NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment . An attacker can trigger a server-side request forgery (SSRF) , which may lead to information disclosure . No specific remediation steps, affected versions, or exploit details are provided in the do...
CVE-2026-100962
NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might cause information disclosure...
CVE-2026-100962
NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might cause information disclosure...
EUVD-2026-121040
NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might cause information disclosure...
PT-2026-141609
NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might cause information disclosure...
CVE-2026-100962: NVIDIA Nemo Deploy: NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could…
NVIDIA NeMo Export-Deploy for all platforms contains a vulnerability in multimodal deployment where an attacker could cause a server-side request forgery. A successful exploit of this vulnerability might cause information disclosure...