Multimodal-Unlearnable-Examples

Ejemplos Multimodales No Aprendibles: Protección de Datos contra el Aprendizaje Contrastivo Multimodal ACM MM2024 Resumen : El aprendizaje contrastivo multimodal MCL ha mostrado avances notables en la clasificación zero-shot al aprender de millones de pares imagen-texto extraídos de Internet. Sin...

bordair-multimodal

Conjunto de Datos de Inyección de Prompts Multimodal 516,588 muestras etiquetadas 251,782 de ataque + 251,576 benignas, más una división de validación del mundo real de 13,230 muestras en cinco versiones del conjunto de datos, más la ingesta de conjuntos de datos externos, cubriendo ataques de...

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...

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...

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....

Multimodal-web-attack-Dataset

MWAD: Un conjunto de datos multimodal de ataques web para la detección de inyección SQL basada en IA Descripción general El conjunto de datos multimodal de ataques web MWAD es un novedoso conjunto de datos etiquetado de ciberseguridad desarrollado como parte de la investigación del autor en...

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...

safety-awareness

Transfer Safety Awareness for Cross-Modal Safety Drift Official implementation of Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models EMNLP 2026 Findings. This repository contains the Qwen3-VL safety-awareness direction pipeline. It extracts a refusal-relate...

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...

vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary vllm/transformersutils/processors/mimov2omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get... directly on user-supplied image and audio URL strings and Image.open... on user-supplied local paths, without the SSRF / allowedlocalmediapath checks that...

GHSA-4HHP-H66F-J5J7 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections

Summary vllm/transformersutils/processors/mimov2omni.py — the multimodal processor for MiMoV2OmniForCausalLM — issues requests.get... directly on user-supplied image and audio URL strings and Image.open... on user-supplied local paths, without the SSRF / allowedlocalmediapath checks that...

ContextHound

ContextHound Herramienta de análisis estático que escanea tu código base en busca de vulnerabilidades de inyección de prompts y seguridad multimodal. Funciona sin conexión, no requiere llamadas a API. El ecosistema de ContextHound ContextHound está disponible en todo tu flujo de trabajo de...

CVE-2026-85686

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...

CVE-2026-85686 ms-swift 4.5.2 Unauthenticated SSRF via Multimodal Media URLs

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...

CVE-2026-85686 ms-swift 4.5.2 Unauthenticated SSRF via Multimodal Media URLs

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...

EUVD-2026-71135

ms-swift 4.5.2 contains a server-side request forgery vulnerability in the swift deploy OpenAI-compatible API that fetches multimodal media URLs without validation or redirect filtering. Unauthenticated attackers can supply arbitrary imageurl, audiourl, or videourl parameters to make the server...

CVE-2026-85686

ms-swift 4.5.2 (ModelScope) contains an unauthenticated SSRF in the swift deploy OpenAI-compatible API. The vulnerable component is vision_utils.py, which fetches multimodal media URLs (image_url , audio_url , video_url ) without URL validation or redirect filtering. An attacker can supply arbitr...

CVE-2026-47617

NVIDIA Dynamo for Linux contains a vulnerability in the multimodal media fetcher where an attacker may cause server-side request forgery via DNS rebinding. A successful exploit of this vulnerability might lead to information disclosure...

CVE-2026-47616

NVIDIA Dynamo for Linux contains a vulnerability in the multimodal media fetcher where an attacker may cause server-side request forgery. A successful exploit of this vulnerability might lead to information disclosure...

CVE-2026-47618

NVIDIA Dynamo for Linux contains a vulnerability in the Rust multimodal media fetcher where an attacker could cause server-side request forgery. A successful exploit of this vulnerability might lead to information disclosure...