Related papers: SoK: How Robust is Audio Watermarking in Generativ…

Speaker recognition systems (SRSs) have recently been shown to be vulnerable to adversarial attacks, raising significant security concerns. In this work, we systematically investigate transformation and adversarial training based defenses…

We provide background on emerging challenges and future directions with media integrity and authentication methods, focusing on distinguishing AI-generated media from authentic content captured by cameras and microphones. We evaluate…

While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection methods can be broadly categorized into passive and…

In the realm of audio watermarking, it is challenging to simultaneously encode imperceptible messages while enhancing the message capacity and robustness. Although recent advancements in deep learning-based methods bolster the message…

The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where…

The emergence of Artificial Intelligence (AI)-driven audio attacks has revealed new security vulnerabilities in voice control systems. While researchers have introduced a multitude of attack strategies targeting voice control systems (VCS),…

To ensure the responsible distribution and use of open-source deep neural networks (DNNs), DNN watermarking has become a crucial technique to trace and verify unauthorized model replication or misuse. In practice, black-box watermarks…

The recent emergence of deepfakes has brought manipulated and generated content to the forefront of machine learning research. Automatic detection of deepfakes has seen many new machine learning techniques, however, human detection…

With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope…

Advancements in deep generative models have made it possible to synthesize images, videos and audio signals that are difficult to distinguish from natural signals, creating opportunities for potential abuse of these capabilities. This…

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a…

Protecting the copyright of user-generated AI images is an emerging challenge as AIGC becomes pervasive in creative workflows. Existing watermarking methods (1) remain vulnerable to real-world adversarial threats, often forced to trade off…

The rapid advancement of deepfake technology poses a significant threat to digital media integrity. Deepfakes, synthetic media created using AI, can convincingly alter videos and audio to misrepresent reality. This creates risks of…

The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding. By embedding information into a noise-tolerant signal such as audio, video, or…

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…

Deepfakes generated by modern generative models pose a serious threat to information integrity, digital identity, and public trust. Existing detection methods are largely reactive, attempting to identify manipulations after they occur and…

As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the…

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 (ML) models are applied in an increasing variety of domains. The availability of large amounts of data and computational resources encourages the development of ever more complex and valuable models. These models are…

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…