Related papers: PGID: Progressive Guided Inversion and Denoising f…
The rapid growth of Artificial Intelligence-Generated Content (AIGC) raises concerns about the authenticity of digital media. In this context, image self-recovery, reconstructing original content from its manipulated version, offers a…
3D Gaussian Splatting (3DGS) has become a crucial method for acquiring 3D assets. To protect the copyright of these assets, digital watermarking techniques can be applied to embed ownership information discreetly within 3DGS models.…
With the explosive growth of internet technology, easy transfer of digital multimedia is feasible. However, this kind of convenience with which authorized users can access information, turns out to be a mixed blessing due to information…
Deep neural network (DNN) watermarking is a suitable method for protecting the ownership of deep learning (DL) models. It secretly embeds an identifier (watermark) within the model, which can be retrieved by the owner to prove ownership. In…
AIGC (AI-Generated Content) has achieved tremendous success in many applications such as text-to-image tasks, where the model can generate high-quality images with diverse prompts, namely, different descriptions in natural languages. More…
Autoregressive (AR) image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent misuse. However, existing in-generation watermarking…
Modern cameras' performance in low-light conditions remains suboptimal due to fundamental limitations in photon shot noise and sensor read noise. Generative image restoration methods have shown promising results compared to traditional…
Digital watermarking is the process of embedding secret information by altering images in an undetectable way to the human eye. To increase the robustness of the model, many deep learning-based watermarking methods use the…
Unauthorized screen-shooting poses a critical data leakage risk. Resisting screen-shooting attacks typically requires high-strength watermark embedding, inevitably degrading the cover image. To resolve the robustness-fidelity conflict,…
Training deep neural networks from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to protect the pre-trained deep neural networks from potential…
The rapid advancement of generative AI has made it increasingly challenging to distinguish between deepfake audio and authentic human speech. To overcome the limitations of passive detection methods, we propose StreamMark, a novel deep…
Recently, Generative Diffusion Models (GDMs) have showcased their remarkable capabilities in learning and generating images. A large community of GDMs has naturally emerged, further promoting the diversified applications of GDMs in various…
Existing deepfake-detection methods focus on passive detection, i.e., they detect fake face images via exploiting the artifacts produced during deepfake manipulation. A key limitation of passive detection is that it cannot detect fake faces…
Advancements in digital technologies make it easy to modify the content of digital images. Hence, ensuring digital images integrity and authenticity is necessary to protect them against various attacks that manipulate them. We present a…
In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key. The proposed method embeds a watermark pattern in a model by using learnable transformed images and allows us…
This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove malicious perturbations in adversarial examples. By…
Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has…
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…
Deep learning techniques have made tremendous progress in a variety of challenging tasks, such as image recognition and machine translation, during the past decade. Training deep neural networks is computationally expensive and requires…
Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…