English
Related papers

Related papers: Black-Box Forgery Attacks on Semantic Watermarks f…

200 papers

Creating a state-of-the-art deep-learning system requires vast amounts of data, expertise, and hardware, yet research into embedding copyright protection for neural networks has been limited. One of the main methods for achieving such…

Cryptography and Security · Computer Science 2020-04-27 William Aiken , Hyoungshick Kim , Simon Woo

As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Anirudh Sundara Rajan , Utkarsh Ojha , Jedidiah Schloesser , Yong Jae Lee

From its acquisition in the camera sensors to its storage, different operations are performed to generate the final image. This pipeline imprints specific traces into the image to form a natural watermark. Tampering with an image disturbs…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Matías Tailanian , Marina Gardella , Álvaro Pardo , Pablo Musé

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

Cryptography and Security · Computer Science 2026-05-26 Zhenxin Ai , Haiyun He

In the expanding field of generative artificial intelligence, integrating robust watermarking technologies is essential to protect intellectual property and maintain content authenticity. Traditionally, watermarking techniques have been…

Machine Learning · Computer Science 2024-10-15 Renyi Yang

With the rapid development of deep neural networks(DNNs), many robust blind watermarking algorithms and frameworks have been proposed and achieved good results. At present, the watermark attack algorithm can not compete with the watermark…

Multimedia · Computer Science 2023-06-23 Xinyu Li

The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models. In this paper, we investigate the…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Marija Ivanovska , Vitomir Štruc

The Internet as a whole does not use secure links, thus information in transit may be vulnerable to interruption as well. The important of reducing a chance of the information being detected during the transmission is being an issue in the…

Multimedia · Computer Science 2012-05-15 Yusuf Perwej , Firoj Parwej , Asif Perwej

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Machine Learning · Computer Science 2024-10-14 Yapei Chang , Kalpesh Krishna , Amir Houmansadr , John Wieting , Mohit Iyyer

The rapid advancement of text-to-image generation systems, exemplified by models like Stable Diffusion, Midjourney, Imagen, and DALL-E, has heightened concerns about their potential misuse. In response, companies like Meta and Google have…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Niyar R Barman , Krish Sharma , Ashhar Aziz , Shashwat Bajpai , Shwetangshu Biswas , Vasu Sharma , Vinija Jain , Aman Chadha , Amit Sheth , Amitava Das

Optical character recognition (OCR) is widely applied in real applications serving as a key preprocessing tool. The adoption of deep neural network (DNN) in OCR results in the vulnerability against adversarial examples which are crafted to…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 Lu Chen , Wei Xu

Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering feature extraction…

Computation and Language · Computer Science 2025-12-04 Anudeex Shetty

Text watermarking aims to subtly embed statistical signals into text by controlling the Large Language Model (LLM)'s sampling process, enabling watermark detectors to verify that the output was generated by the specified model. The…

Machine Learning · Computer Science 2025-05-13 Yixin Cheng , Hongcheng Guo , Yangming Li , Leonid Sigal

As companies continue to invest heavily in larger, more accurate and more robust deep learning models, they are exploring approaches to monetize their models while protecting their intellectual property. Model licensing is promising, but…

Cryptography and Security · Computer Science 2020-12-04 Huiying Li , Emily Wenger , Shawn Shan , Ben Y. Zhao , Haitao Zheng

The increasing use of Large Language Models (LLMs) for generating highly coherent and contextually relevant text introduces new risks, including misuse for unethical purposes such as disinformation or academic dishonesty. To address these…

Computation and Language · Computer Science 2024-10-16 Zhenyu Xu , Kun Zhang , Victor S. Sheng

Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…

Cryptography and Security · Computer Science 2026-02-24 Dara Bahri , John Wieting

Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises…

Cryptography and Security · Computer Science 2025-01-29 Wenjie Qu , Wengrui Zheng , Tianyang Tao , Dong Yin , Yanze Jiang , Zhihua Tian , Wei Zou , Jinyuan Jia , Jiaheng Zhang

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Machine Learning · Computer Science 2022-05-23 Shuo Wang , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen , Tianle Chen

With the widespread use of deep neural networks (DNNs) in many areas, more and more studies focus on protecting DNN models from intellectual property (IP) infringement. Many existing methods apply digital watermarking to protect the DNN…

Cryptography and Security · Computer Science 2022-07-11 Lina Lin , Hanzhou Wu

The functionality of a deep learning (DL) model can be stolen via model extraction where an attacker obtains a surrogate model by utilizing the responses from a prediction API of the original model. In this work, we propose a novel…

Cryptography and Security · Computer Science 2022-07-28 Abhishek Chakraborty , Daniel Xing , Yuntao Liu , Ankur Srivastava