Related papers: Unsafe2Safe: Controllable Image Anonymization for …
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…
Stable Diffusion (SD) customization approaches enable users to personalize SD model outputs, greatly enhancing the flexibility and diversity of AI art. However, they also allow individuals to plagiarize specific styles or subjects from…
Text-to-image generative models are becoming increasingly popular and accessible to the general public. As these models see large-scale deployments, it is necessary to deeply investigate their safety and fairness to not disseminate and…
Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too…
Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled distributions. Such synthetic datasets can augment the…
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…
Recent advances in visual-language alignment have endowed vision-language models (VLMs) with fine-grained image understanding capabilities. However, this progress also introduces new privacy risks. This paper first proposes a novel privacy…
The growing demand for customized visual content has led to the rise of personalized text-to-image (T2I) diffusion models. Despite their remarkable potential, they pose significant privacy risk when misused for malicious purposes. In this…
Dataset distillation aims to create a small and highly representative synthetic dataset that preserves the essential information of a larger real dataset. Beyond reducing storage and computational costs, related approaches offer a promising…
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…
The rise in harmful online content not only distorts public discourse but also poses significant challenges to maintaining a healthy digital environment. In response to this, we introduce a multimodal dataset uniquely crafted for…
Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting deepfakes, at scale, remains a very challenging task that often…
Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically sensitive contexts. This challenge is amplified by the increasing realism of modern generative…
Text-to-image (T2I) models have rapidly advanced, enabling the generation of high-quality images from text prompts across various domains. However, these models present notable safety concerns, including the risk of generating harmful,…
Recent advancements in controllable human image generation have led to zero-shot generation using structural signals (e.g., pose, depth) or facial appearance. Yet, generating human images conditioned on multiple parts of human appearance…
The modern surge in camera usage alongside widespread computer vision technology applications poses significant privacy and security concerns. Current artificial intelligence (AI) technologies aid in recognizing relevant events and…
Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and…
Advances in image restoration and enhancement techniques have led to discussion about how such algorithmscan be applied as a pre-processing step to improve automatic visual recognition. In principle, techniques like deblurring and…
Probing or fine-tuning (large-scale) pre-trained models results in state-of-the-art performance for many NLP tasks and, more recently, even for computer vision tasks when combined with image data. Unfortunately, these approaches also entail…
Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence. Prevalent methods tackling this problem use differential privacy (DP) or obfuscation techniques to protect the privacy of…