openstego

OpenStego OpenStego は、以下の2つの機能を提供するステガノグラフィーアプリケーションです。 1. データ隠蔽: 画像ファイル内にあらゆるデータを隠蔽できます。 2. 透かし: 不可視の署名で画像ファイルに透かしを入れます。不正なファイルコピーを検出するために使用できます。 使用方法 GUIの場合: インストーラーを使用した場合は、OpenStego のメニューショートカットを使用してください。zip ダウンロードの場合は、バンドルされているバッチファイルまたはシェルスクリプトを使用して GUI を起動します。 root@kitploit: openstego.bat...

openstego

OpenStego OpenStego is a steganography application that provides two functionalities: 1. Data Hiding: It can hide any data within an image file. 2. Watermarking: Watermarking image files with an invisible signature. It can be used to detect unauthorized file copying. Usage For GUI: Use menu...

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...

craw

CRAW: Codec Robust Audio Watermarking Source code for CRAW , a robust audio watermarking method built on STFT-magnitude-domain embedding. An encoder embeds a binary message into an audio clip's magnitude spectrogram phase is preserved from the clean signal; a decoder recovers the message under a...

WeaveMark

WeaveMark 通过编码载荷扩展实现鲁棒且可扩展的多比特 LLM 水印 的参考实现。 WeaveMark 在保持 token 分布无偏的同时，将 k 比特消息嵌入到 LLM 生成的文本中。它结合了编码载荷扩展（每 token 在 ℓ 层上承载 κ 个码字比特，并采用上下文打乱的层→比特分配）、基于每比特投票余量的软判决 ECC 解码，以及无偏多层重加权（每个方向与一次上下文抛硬币结果进行 XOR）。专用的零比特层从上下文中划分出来而非从消息中划分，从而提供与消息无关的存在性检测。 目录结构 root@kitploit: weavemark/ 库 watermark.py...

Stego-Lab

Stego-Lab ステガノグラフィ。EXIF。透かし。デコード。バッチ。 iPhone、iPad、macOS向けのプロフェッショナルな画像プライバシーワークフロー。 Webサイト · GitLab · プロジェクトページ · プライバシーポリシー · プレスキット · サポート · ライセンス Stego-Labの理由 Stego-Labは、通常複数のアプリに分散しているワークフロー（不可視ステガノグラフィ、可視透かし入れ、EXIF編集、デコード、バッチ処理）を1つにまとめます。...

SwordStamp

SwordStamp SwordStamp adds order-robust detection and semantic-span units to embedding-based semantic watermarks. This artifact contains the exact paper configuration, generation and detection code, the unchanged attack suite, quality evaluation, and deterministic result extraction and plotting...

nullorigin

NullOrigin 🛡️ 通用 AI 溯源与水印净化中间件 研究产物——仅用于水印鲁棒性评估。 🔬 仅限研究使用 NullOrigin 是一个研究产物。其发布旨在支持关于水印鲁棒性的学术与独立研究，不用于任何其他目的。 水印方案是一种安全声明，而安全声明只有在有人尝试破解它时才有意义。本项目实现的相关文献——Kirchenbauer 等人关于 KGW 的研究、Krishna 等人关于释义攻击的研究、Boucher 和 Anderson 关于 Trojan Source...

CC_Watermark

用于无失真文本水印的最优耦合 用于无失真文本水印的最优耦合 的官方代码 摘要 大型语言模型（LLM）现在能够生成与人类内容无法区分的文本。 这推动了水印技术的发展，水印通过在 LLM 生成的文本中印记"信号"，同时对 LLM 输出的扰动最小。 本文对一次性（one-shot）场景下的文本水印进行了分析。 通过带辅助信息的假设检验视角，我们系统地阐述并分析了水印检测能力与生成文本质量失真之间的基本权衡。 我们认为水印设计的一个关键组成部分是在与水印检测器共享的辅助信息与 LLM 词汇表的随机划分之间生成一种耦合。 我们的分析确定了在满足最小熵约束的最坏情况 LLM...

covertchannels-steganography

很多人问我如何入门隐写术/隐蔽信道领域，或如何提升相关技能。我编写这份合集，提供一些我使用和阅读过的优秀参考资料、工具和书籍（后续我会补充更多）。 书籍与论文/文章 信息隐藏技术：隐写术与数字水印 -...

From Noise to Meaning: Meaningful Secret Sharing with Tamper Detection for Facial Recognition

Popularity of AI-based face recognition system directly demands protection of sensitive biometric data used for training. Visual secret sharing is an interesting idea, as it splits facial images into secret shares that look random and spread across many institutions. However, these shares look li...

Cryptanalysis of Pseudorandom Error-Correcting Codes

Pseudorandom error-correcting codes PRC is a novel cryptographic primitive proposed at CRYPTO 2024. Due to the dual capability of pseudorandomness and error correction, PRC has been recognized as a promising foundational component for watermarking AI-generated content. However, the security of PR...

Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models

Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing model-generated output from text written by humans. Digital...

DITTO: A Spoofing Attack Framework on Watermarked LLMs Via Knowledge Distillation

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a sophisticated attack that allows a malicious model to generate te...

The Impact of Audio Watermarking on Audio Anti-Spoofing Countermeasures

This paper presents the first study on the impact of audio watermarking on spoofing countermeasures. While anti-spoofing systems are essential for securing speech-based applications, the influence of widely used audio watermarking, originally designed for copyright protection, remains largely...

Cryptographic Backdoor for Neural Networks: Boon and Bane

In this paper we show that cryptographic backdoors in a neural network NN can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted cryptographic backdoor enables powerful and invisible attack on t...

Risk Assessment and Security Analysis of Large Language Models

As large language models LLMs expose systemic security challenges in high risk applications, including privacy leaks, bias amplification, and malicious abuse, there is an urgent need for a dynamic risk assessment and collaborative defence framework that covers their entire life cycle. This paper...

Hot-Swap MarkBoard: an Efficient Black-Box Watermarking Approach for Large-Scale Model Distribution

Recently, Deep Learning DL models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property IP risks, as models are distributed on numerous local devices, making them...

Removing Box-Free Watermarks for Image-To-Image Models Via Query-Based Reverse Engineering

The intellectual property of deep generative networks GNets can be protected using a cascaded hiding network HNet which embeds watermarks or marks into GNet outputs, known as box-free watermarking. Although both GNet and HNet are encapsulated in a black box called operation network, or ONet, with...

WaveVerify: a Novel Audio Watermarking Framework for Media Authentication and Combatting Deepfakes

The rapid advancement of voice generation technologies has enabled the synthesis of speech that is perceptually indistinguishable from genuine human voices. While these innovations facilitate beneficial applications such as personalized text-to-speech systems and voice preservation, they have als...