Lucene search
+L

107 matches found

Kitploit
Kitploit
added 2026/09/18 10:06 p.m.5 views

openstego

OpenStego OpenStego — это приложение для стеганографии, которое предоставляет две функции: 1. Сокрытие данных: может скрывать любые данные в файле изображения. 2. Водяной знак: нанесение на файлы изображений невидимой подписи. Он может использоваться для обнаружения несанкционированного копирован...

6AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/18 10:06 p.m.178 views

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...

5.8AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/17 11:09 p.m.9 views

Watermark_Spoofing

오디오 워터마킹이 오디오 안티-스푸핑 대응책에 미치는 영향 이 저장소는 본 논문 오디오 워터마킹이 오디오 안티-스푸핑 대응책에 미치는 영향 의 공식 구현을 제공합니다. 대화형 데모와 시각화 자료는 여기에서 확인하세요. 구성 내용 1. 워터마크-스푸핑 데이터셋 WSD — 워터마킹된 평가 및 학습 세트를 생성하기 위한 스크립트와 라벨 파일. 2. 지식 보존 워터마크 학습 KPWL — KPWL 프레임워크와 실험을 재현하기 위한 스크립트. 워터마크-스푸핑 데이터셋 WSD WSD는 공개 말뭉치로부터 파생되었으며, 원본 데이터셋을 기준으...

6.1AI score
SaveExploits0References4
Kitploit
Kitploit
added 2026/09/17 8:51 p.m.8 views

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...

5.9AI score
SaveExploits0References7
Kitploit
Kitploit
added 2026/09/17 2:46 a.m.7 views

WeaveMark

WeaveMark 코딩된 페이로드 확산을 통한 견고하고 확장 가능한 멀티비트 LLM 워터마킹 의 참조 구현입니다. WeaveMark는 토큰 분포를 편향시키지 않으면서 k 비트 메시지를 LLM 생성 텍스트에 삽입합니다. 이는 코딩된 페이로드 확산ℓ 레이어에 걸쳐 토큰당 κ 코드워드 비트, 컨텍스트 셔플 레이어→비트 할당, 비트별 투표 마진의 소프트 결정 ECC 디코딩, 그리고 편향 없는 멀티레이어 재가중치각 방향을 컨텍스트 코인 플립과 XOR를 결합합니다. 메시지가 아닌 컨텍스트에서 분할된 전용 제로비트 레이어는 메시지와 무관한...

6AI score
SaveExploits0References1
Kitploit
Kitploit
added 2026/09/16 4:24 p.m.12 views

Stego-Lab

Stego-Lab Стеганография. EXIF. Водяные знаки. Декодирование. Пакетная обработка. Профессиональные рабочие процессы для обеспечения конфиденциальности изображений на iPhone, iPad и macOS. Веб-сайт · GitLab · Страница проекта · Политика конфиденциальности · Пресс-кит · Поддержка · Лицензия Почему...

5.8AI score
SaveExploits0References22
Kitploit
Kitploit
added 2026/09/13 11:38 p.m.8 views

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...

6AI score
SaveExploits0References2
Kitploit
Kitploit
added 2026/09/13 9:34 p.m.11 views

nullorigin

NullOrigin 🛡️ 범용 AI 출처 및 워터마크 정화 미들웨어 연구 산출물 — 워터마킹 견고성 평가 전용입니다. 🔬 연구 전용 NullOrigin은 연구 산출물입니다. 워터마킹 견고성에 대한 학술적·독립적 연구를 지원하기 위해 공개되었으며, 그 외의 목적은 없습니다. 워터마킹 기법은 보안 주장이며, 보안 주장은 누군가 그것을 깨보려고 시도할 때만 의미가 있습니다. 이 프로젝트가 구현하는 문헌들 — KGW에 대한 Kirchenbauer 등, 패러프레이즈 공격에 대한 Krishna 등, Trojan Source에 대한...

6.2AI score
SaveExploits0References5
Kitploit
Kitploit
added 2026/09/13 7:10 p.m.7 views

CC_Watermark

왜곡 없는 텍스트 워터마킹을 위한 최적 커플링 왜곡 없는 텍스트 워터마킹을 위한 최적 커플링 의 공식 코드 초록 대규모 언어 모델LLM은 이제 인간이 생성한 콘텐츠와 구별할 수 없는 텍스트를 생성할 수 있게 되었다. 이는 LLM 출력을 최소한으로 교란하면서 LLM이 생성한 텍스트에 '신호'를 새겨 넣는 워터마크 개발을 촉진했다. 본 논문은 원샷one-shot 설정에서 텍스트 워터마킹에 대한 분석을 제공한다. 부가 정보를 활용한 가설 검정의 관점에서, 우리는 워터마크 탐지 성능과 생성된 텍스트 품질 왜곡 사이의 근본적인...

5.8AI score
SaveExploits0
Kitploit
Kitploit
added 2026/09/13 12:01 p.m.10 views

covertchannels-steganography

많은 사람들이 스테가노그래피/은닉 채널 분야에 어떻게 입문하는지, 또는 실력을 어떻게 향상시킬 수 있는지 묻습니다. 저는 제가 사용하고 읽은 몇 가지 좋은 참고 자료, 도구, 서적을 통해 그들을 돕기 위해 이 모음집을 작성했습니다 곧 더 추가하겠습니다. 도서 및 논문/기사 스테가노그래피와 디지털 워터마킹을 위한 정보 은닉 기법 -...

5.7AI score
SaveExploits0References29
Packet Storm News
Packet Storm News
added 2026/08/09 12:00 a.m.12 views

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...

5.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/12/19 12:00 a.m.17 views

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...

6.7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/12/15 12:00 a.m.23 views

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...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/10/12 12:00 a.m.9 views

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...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/09/25 12:00 a.m.8 views

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...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/09/24 12:00 a.m.10 views

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...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/08/24 12:00 a.m.10 views

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...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/07/28 12:00 a.m.15 views

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...

6.6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/07/23 12:00 a.m.11 views

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...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/07/23 12:00 a.m.12 views

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...

6.9AI score
SaveExploits0
Rows per page
Query Builder