Related papers: Wide spread spectrum watermarking with side inform…
Diffusion models have made substantial advances in recent years, enabling high-quality image synthesis; however, the widespread dissemination and reuse of their outputs have introduced new challenges in intellectual property protection and…
As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical…
Spread spectrum, widely employed in modern digital wireless terrestrial radio systems, chooses a signal with a noise-like character and much higher bandwidth than necessary. This paper advocates spread spectrum modulation for interstellar…
Watermarking is a principled approach for tracing the provenance of large language model (LLM) outputs, but its deployment in practice is hindered by inference inefficiency. Speculative sampling accelerates inference, with efficiency…
Robust invisible watermarking embeds hidden information in images such that the watermark can survive various manipulations. However, the emergence of powerful diffusion-based image generation and editing techniques poses a new threat to…
One of the effective methods for the preservation of copyright ownership of digital media is watermarking. Different watermarking techniques try to set a tradeoff between robustness and transparency of the process. In this research work, we…
Visible watermarks, while instrumental in protecting image copyrights, frequently distort the underlying content, complicating tasks like scene interpretation and image editing. Visible watermark removal aims to eliminate the interference…
Visible watermark plays an important role in image copyright protection and the robustness of a visible watermark to an attack is shown to be essential. To evaluate and improve the effectiveness of watermark, watermark removal attracts…
Blind watermarking provides powerful evidence for copyright protection, image authentication, and tampering identification. However, it remains a challenge to design a watermarking model with high imperceptibility and robustness against…
Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by…
Due to the limited available bandwidth and dynamic channel, data rates are extremely limited in underwater acoustic (UWA) communications. Addressing this concern, in-band fullduplex (IBFD) has the potential to double the efficiency in a…
The wide deployment of Face Recognition (FR) systems poses privacy risks. One countermeasure is adversarial attack, deceiving unauthorized malicious FR, but it also disrupts regular identity verification of trusted authorizers, exacerbating…
The rapid development of Artificial Intelligence Generated Content (AIGC) has led to significant progress in video generation, but also raises serious concerns about intellectual property protection and reliable content tracing.…
Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…
Recent progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output…
We propose a novel audio watermarking system that is robust to the distortion due to the indoor acoustic propagation channel between the loudspeaker and the receiving microphone. The system utilizes a set of new algorithms that effectively…
Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the…
Differing from the conventional communication system paradigm that models information source as a sequence of (i.i.d. or stationary) random variables, the semantic approach aims at extracting and sending the high-level features of the…
High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual property protection and the misuse of synthetic media. To…
Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Processing (NLP). Prior studies have shown that EaaS can be prone…