Related papers: Uncovering and Mitigating Destructive Multi-Embedd…
The proliferation of Deep Neural Networks (DNN) in commercial applications is expanding rapidly. Simultaneously, the increasing complexity and cost of training DNN models have intensified the urgency surrounding the protection of…
The growing threat of deepfakes and manipulated media necessitates a radical rethinking of media authentication. Existing methods for watermarking synthetic data fall short, as they can be easily removed or altered, and current deepfake…
Face anti-spoofing (FAS) is a vital component of remote biometric authentication systems based on facial recognition, increasingly used across web-based applications. Among emerging threats, video injection attacks -- facilitated by…
Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep…
Deep neural networks (DNNs) deployed in a cloud often allow users to query models via the APIs. However, these APIs expose the models to model extraction attacks (MEAs). In this attack, the attacker attempts to duplicate the target model by…
Deep neural networks (DNNs) have been used in digital forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to examine whether they are secure against adversarial attacks. We…
In practice, metric analysis on a specific train and test dataset does not guarantee reliable or fair ML models. This is partially due to the fact that obtaining a balanced, diverse, and perfectly labeled dataset is typically expensive,…
As deepfake technologies continue to advance, passive detection methods struggle to generalize with various forgery manipulations and datasets. Proactive defense techniques have been actively studied with the primary aim of preventing…
Watermarks for AI-generated images are meant to support downstream decisions about provenance, manipulation, and trust. In the settings that motivate watermark removal, therefore, success means more than causing the watermark test to fail.…
As AI-generated sensitive images become more prevalent, identifying their source is crucial for distinguishing them from real images. Conventional image watermarking methods are vulnerable to common transformations like filters, lossy…
Foundational generative models should be traceable to protect their owners and facilitate safety regulation. To achieve this, traditional approaches embed identifiers based on supervisory trigger-response signals, which are commonly known…
Deepfake technologies have rapidly advanced with modern generative AI, and face swapping in particular poses serious threats to privacy and digital security. Existing proactive defenses mostly rely on pixel-level perturbations, which are…
Recent advancements in Generative Adversarial Networks (GANs) have enabled photorealistic image generation with high quality. However, the malicious use of such generated media has raised concerns regarding visual misinformation. Although…
Latent diffusion models have exhibited considerable potential in generative tasks. Watermarking is considered to be an alternative to safeguard the copyright of generative models and prevent their misuse. However, in the context of model…
The rapid progress of Generative Artificial Intelligence (GenAI) has enabled the effortless synthesis of high-quality visual content, while simultaneously raising pressing concerns about intellectual property protection, authenticity, and…
Deep neural networks are vulnerable to adversarial attacks. The literature is rich with algorithms that can easily craft successful adversarial examples. In contrast, the performance of defense techniques still lags behind. This paper…
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…
As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However,…
Ownership verification is currently the most critical and widely adopted post-hoc method to safeguard model copyright. In general, model owners exploit it to identify whether a given suspicious third-party model is stolen from them by…
In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed.…