Related papers: Contrasting Deepfakes Diffusion via Contrastive Le…

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space…

This paper present a comprehensive comparative analysis of supervised and self-supervised models for deepfake detection. We evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

The rapid advancement of deepfake generation techniques poses significant threats to public safety and causes societal harm through the creation of highly realistic synthetic facial media. While existing detection methods demonstrate…

Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images. Most existing methods address this…

Learning node-level representations of heterophilic graphs is crucial for various applications, including fraudster detection and protein function prediction. In such graphs, nodes share structural similarity identified by the equivalence…

Leveraging StyleGAN's expressivity and its disentangled latent codes, existing methods can achieve realistic editing of different visual attributes such as age and gender of facial images. An intriguing yet challenging problem arises: Can…

Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise to a new challenge in the form…

After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains…

The increasing realism and accessibility of deepfakes have raised critical concerns about media authenticity and information integrity. Despite recent advances, deepfake detection models often struggle to generalize beyond their training…

Detecting falsified faces generated by Deepfake technology is essential for safeguarding trust in digital communication and protecting individuals. However, current detectors often suffer from a dual-overfitting: they become overly…

Recent generative models demonstrate impressive performance on synthesizing photographic images, which makes humans hardly to distinguish them from pristine ones, especially on realistic-looking synthetic facial images. Previous works…

Counterfeit apps impersonate existing popular apps in attempts to misguide users to install them for various reasons such as collecting personal information or spreading malware. Many counterfeits can be identified once installed, however…

In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been applied because the input is a set of images in which…

Current image quality assessment methods are heavily biased towards global distortions (e.g., noise, blur), neglecting local perceptual artifacts such as ghosting, lens flare, and moire effects. Although significant progress has been made…

Recent self-supervised models have demonstrated equal or better performance than supervised methods, opening for AI systems to learn visual representations from practically unlimited data. However, these methods are typically…

The rapid advancement of generative AI has enabled the mass production of photorealistic synthetic images, blurring the boundary between authentic and fabricated visual content. This challenge is particularly evident in deepfake scenarios…

Despite the recent attention to DeepFakes, one of the most prevalent ways to mislead audiences on social media is the use of unaltered images in a new but false context. To address these challenges and support fact-checkers, we propose a…

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…