Lucene search
+L

403 matches found

Kitploit
Kitploit
•added 2026/10/05 4:45 p.m.•14 views

remove-ai-watermarks

Remove AI Watermarks Remove AI provenance marks from images and video you generated yourself: known visible labels such as the Google Gemini sparkle watermark and vendor text marks; invisible pixel watermarks through direct local-format disruption or diffusion regeneration; C2PA, EXIF, XMP, IPTC,...

6AI score
SaveExploits0References7
CVE
CVE
•added 2026/10/05 4:07 p.m.•5 views

CVE-2026-102776

The Joomla Extension - svenbluege.de 's Event Gallery extension (versions

5.1CVSS5.7AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/05 4:01 p.m.•10 views

Watermark_Spoofing

EL IMPACTO DEL MARCADO DE AGUA DE AUDIO EN LAS CONTRAMEDIDAS ANTI-SPOOFING DE AUDIO Este repositorio proporciona la implementación oficial de nuestro artículo: EL IMPACTO DEL MARCADO DE AGUA DE AUDIO EN LAS CONTRAMEDIDAS ANTI-SPOOFING DE AUDIO . Explora la demo interactiva y las visualizaciones...

6.3AI score
SaveExploits0References4
Kitploit
Kitploit
•added 2026/10/05 2:36 p.m.•18 views

watermarks-remover

| | | || | | |/ |/| || |/ |/ |/ | |/| | | | | | |/ ||| | | | | | \ | | | | | \ | \ | \ | | | || / | | \ watermarks-remover Habilidad de agente + servicio Python de biblioteca estándar para eliminar marcas de procedencia de IA de múltiples proveedores de texto y archivos — para privacidad e...

6.1AI score
SaveExploits0References7
Kitploit
Kitploit
•added 2026/10/05 2:06 p.m.•15 views

reverse-SynthID-text

SynthID 水印逆向工程 概述 该目录包含用于分析和移除AI生成文本中SynthID水印的工具。该水印由Google DeepMind开发,并于2024年发表在《自然》杂志上。 SynthID 工作原理 水印生成过程 1. N-gram 上下文 :对于每个词元位置,SynthID 将之前的 ngramlen - 1 个词元(默认:4个词元)视为上下文。 2. 哈希计算 :计算以下内容的哈希: 上下文词元 候选的下一个词元 一组秘密水印密钥(默认30个) 3. G值分配 :哈希用于为每个密钥层的每个可能的下一个词元分配一个二进制g值(0或1)。 4. 概率修改...

6.2AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/05 1:35 p.m.•65 views

stegcloak

StegCloak The Cloak of Invisibility for your texts StegCloak is a pure JavaScript steganography module designed in functional programming style, to hide secrets inside text by compressing and encrypting the secret before cloaking it with special unicode invisible characters. It can be used to...

6.1AI score
SaveExploits0References6
Kitploit
Kitploit
•added 2026/10/05 7:57 a.m.•49 views

tiktok-scraper

TikTok Scraper & Downloader Scrape and download useful information from TikTok. No login or password are required This is not an official API support and etc. This is just a scraper that is using TikTok Web API to scrape media and related meta information. Content Features To Do Contribution...

6AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/10/05 7:06 a.m.•15 views

reverse-SynthID

逆向工程 SynthID 通过频谱分析发现、检测并精确移除 Google 的 AI 水印 访问我们的 PitchHut 本分支为 V3 绕过方案添加了一个拖放式桌面应用程序,设置后无需命令行。参见 gui/README.md 了解设置和使用方法。 水印的样子 SynthID 将一种难以察觉的模式直接编码到像素值中。在 Gemini 生成的纯白色 图像上,水印几乎占据了整个信号。放大高频残差后看起来像这样: 从纯白 Gemini 图像中提取的放大 SynthID 载波模式。对角线条纹是水印的空间频率特征——这是我们频谱攻击的目标。 概述 本项目逆向工程了 Google 的 SynthID...

6.1AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/10/04 11:52 p.m.•19 views

claude-awm

claude-awm: can you scrub a SynthID text watermark by editing the text? Yes, but only one family of attack works, and it isn't the one everyone assumes. Unicode variation selectors category Mn, U+FE00 to U+FE0F and U+E0100 to U+E01EF drive the detector below threshold and stay there. Every other...

6.2AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/10/04 9:35 p.m.•13 views

nullorigin

NullOrigin 🛡️ Middleware universal de procedencia y saneamiento de marcas de agua para IA Artefacto de investigación: solo para evaluación de robustez de marcas de agua. 🔬 Solo para uso en investigación NullOrigin es un artefacto de investigación. Se publica para apoyar el estudio académico e...

6.2AI score
SaveExploits0References3
Packet Storm News
Packet Storm News
•added 2026/09/27 12:00 a.m.•8 views

DeMark: A Query-Free Black-Box Attack for Quality-Preserving Audio Watermark Removal

Audio watermarking protects digital speech by embedding imperceptible signals for ownership verification and misuse tracing. However, the security of learning-based watermarking remains insufficiently understood under realistic adversarial removal, where attackers cannot access or query the...

6AI score
SaveExploits0
EUVD
EUVD
•added 2026/09/17 5:16 p.m.•25 views

EUVD-2026-52282

Grav: Path Traversal in ImageMedium::watermark — arbitrary file disclosure via publicly-cached images...

8.7CVSS7.4AI score0.00548EPSS
SaveExploits0References6
Github Security Blog
Github Security Blog
•added 2026/09/17 5:16 p.m.•16 views

Grav: Path Traversal in ImageMedium::watermark() — arbitrary file disclosure via publicly-cached images

Reported by: Nihad Huseynli @nihaddhuseynli https://github.com/nihaddhuseynli — [email protected] ▎ Note: I attempted to report this via [email protected] first, per SECURITY.md, but the email bounced with 550 5.1.1 Address does not exist. Filing directly here instead. Path Traversal i...

8.7CVSS7.3AI score0.00548EPSS
SaveExploits0References7Affected Software1
Kitploit
Kitploit
•added 2026/09/04 5:30 a.m.•12 views

remove-ai-watermarks v0.37.1

Remove AI Watermarks Remove AI provenance marks from images and video you generated yourself: known visible labels such as the Google Gemini sparkle watermark and vendor text marks; invisible pixel watermarks through direct local-format disruption or diffusion regeneration; C2PA, EXIF, XMP, IPTC,...

6AI score
SaveExploits0References7
Kitploit
Kitploit
•added 2026/08/30 12:20 p.m.•21 views

watermarks-remover v0.5.0

| | | || | | |/ |/| || |/ |/ |/ | |/| | | | | | |/ ||| | | | | | \ | | | | | \ | \ | \ | | | || / | | \ watermarks-remover Agent skill + stdlib Python service to strip multi-vendor AI provenance marks from text and files — for privacy and hygiene on content you own. The skill is a thin client:...

5.9AI score
SaveExploits0References8
The Hacker News
The Hacker News
•added 2026/08/11 11:35 a.m.•16 views

Researchers Built a Fake Crypto Startup and Hired Three Suspected North Korean IT Workers

Security researchers invented a cryptocurrency startup, advertised developer jobs, and hired three people they believe were North Korean operatives. Every virtual machine the company issued was recording. The onboarding paperwork is the part hiring teams can use. The first hire claimed to live in...

5.7AI score
SaveExploits0
OSSF Malicious Packages
OSSF Malicious Packages
•added 2026/08/05 2:59 p.m.•26 views

Malicious code in bigops-watermark (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e1eba25818a15259edb9be7c7629e7319599a0ba7ac7a665f976c78ffb1e56f3 On require of the package, index.js unconditionally loads support.js, whose init runs at module load. It selects a platform-specific endpoint, fetche...

5.6AI score
SaveExploits0References2
OSV
OSV
•added 2026/08/05 2:59 p.m.•18 views

MAL-2026-12857 Malicious code in bigops-watermark (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e1eba25818a15259edb9be7c7629e7319599a0ba7ac7a665f976c78ffb1e56f3 On require of the package, index.js unconditionally loads support.js, whose init runs at module load. It selects a platform-specific endpoint, fetche...

5.6AI score
SaveExploits0References2
BDU FSTEC
BDU FSTEC
•added 2026/08/05 12:00 a.m.•18 views

The vulnerability of the ImageMedium::watermark() function in the Grav CMS system allows a hacker to disclose protected information.

The vulnerability of the ImageMedium::watermark function in the Grav CMS system is related to an incorrect limitation on the path to the catalog. Exploiting this vulnerability could allow a malicious actor to disclose protected information...

7.8CVSS5.5AI score0.00548EPSS
SaveExploits0References2Affected Software1
Tenable Nessus
Tenable Nessus
•added 2026/08/05 12:00 a.m.•13 views

Linux Distros Unpatched Vulnerability : CVE-2026-53502

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Thumbor is an open-source photo thumbnail service by globo.com. Prior to 7.8.0, fileloader decodes percent-encoded path segments after its root-boundary...

8.7CVSS5.9AI score0.00522EPSS
SaveExploits0References2
Rows per page
Query Builder