Lucene search
+L

617 matches found

Kitploit
Kitploit
•added 2026/11/17 2:40 p.m.•28 views

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...

6.3AI score
SaveExploits0References4
Kitploit
Kitploit
•added 2026/11/17 11:54 a.m.•60 views

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...

6.3AI score
SaveExploits0References28
Kitploit
Kitploit
•added 2026/11/16 7:31 p.m.•31 views

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...

6.2AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/11/16 6:39 a.m.•56 views

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...

6.1AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/11/15 5:51 p.m.•22 views

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...

6.2AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/15 3:56 p.m.•24 views

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,...

6.3AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/11/15 9:14 a.m.•33 views

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,...

6.1AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/15 8:17 a.m.•49 views

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...

9.8CVSS7.5AI score0.18287EPSS
SaveExploits2References6
Nuclei
Nuclei
•added 2026/11/15 2:03 a.m.•86 views

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....

9.8CVSS6.8AI score0.18287EPSS
SaveExploits2References3
CVE
CVE
•added 2026/11/13 9:35 a.m.•21 views

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...

8.7CVSS6AI score0.00464EPSS
SaveExploits0References3
osv_cve
osv_cve
•added 2026/11/13 9:35 a.m.•8 views

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...

8.7CVSS6.1AI score
SaveExploits0References5
EUVD
EUVD
•added 2026/11/13 9:35 a.m.•8 views

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...

8.7CVSS6AI score0.00464EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/11/13 12:00 a.m.•6 views

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...

8.7CVSS5.9AI score0.00464EPSS
SaveExploits0References7
NVD
NVD
•added 2026/11/10 1:18 p.m.•7 views

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...

5.3CVSS0.00224EPSS
SaveExploits0References3
CVE
CVE
•added 2026/11/10 12:58 p.m.•14 views

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...

5.3CVSS6AI score0.00224EPSS
SaveExploits0References3
Mend
Mend
•added 2026/11/10 12:58 p.m.•5 views

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...

6.9CVSS6AI score0.00224EPSS
SaveExploits0References3
Cvelist
Cvelist
•added 2026/11/10 12:58 p.m.•31 views

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...

5.3CVSS0.00224EPSS
SaveExploits0References3
EUVD
EUVD
•added 2026/11/10 12:58 p.m.•11 views

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...

5.3CVSS6AI score0.00224EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/11/10 12:00 a.m.•8 views

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...

5.3CVSS6AI score0.00224EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/11/10 12:00 a.m.•9 views

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...

5.3CVSS6AI score0.00224EPSS
SaveExploits0References2
Rows per page
Query Builder