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

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright…

Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they rely either on simple superposition in the noise space or…

AI watermarking embeds invisible signals within images to provide provenance information and identify content as AI-generated. In this paper, we introduce MarkSweep, a novel watermark removal attack that effectively erases the embedded…

AI-Generated Content (AIGC) is rapidly expanding, with services using advanced generative models to create realistic images and fluent text. Regulating such content is crucial to prevent policy violations, such as unauthorized…

The rapid advancement of AI technology, particularly in generating AI-generated content (AIGC), has transformed numerous fields, e.g., art video generation, but also brings new risks, including the misuse of AI for misinformation and…

Recent advances in Text-to-Speech (TTS) and Voice-Conversion (VC) using generative Artificial Intelligence (AI) technology have made it possible to generate high-quality and realistic human-like audio. This poses growing challenges in…

The advancements in generative AI have enabled the improvement of audio synthesis models, including text-to-speech and voice conversion. This raises concerns about its potential misuse in social manipulation and political interference, as…

Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and extensive popularity, they are not without their exploitable flaws.…

Current image watermarking technologies are predominantly categorized into text watermarking techniques and image steganography; however, few methods can simultaneously handle text and image-based watermark data, which limits their…

Audio deepfake detection is an emerging active topic. A growing number of literatures have aimed to study deepfake detection algorithms and achieved effective performance, the problem of which is far from being solved. Although there are…

There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…

The rapid advancement of generative models has led to the synthesis of real-fake ambiguous voices. To erase the ambiguity, embedding watermarks into the frequency-domain features of synthesized voices has become a common routine. However,…

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…

While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks,…

With the rapid proliferation of generative models, such as diffusion models, digital watermarking has emerged as a crucial solution for identifying AI-generated images. Modern post-hoc watermarking schemes use neural networks to achieve an…

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has…

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…

In recent years, watermarking generative tabular data has become a prominent framework to protect against the misuse of synthetic data. However, while most prior work in watermarking methods for tabular data demonstrate a wide variety of…

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…

Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial…