相关论文: Exploiting Alpha Transparency In Language And Visi…

The use of deep learning for human identification and object detection is becoming ever more prevalent in the surveillance industry. These systems have been trained to identify human body's or faces with a high degree of accuracy. However,…

Deep hiding, embedding images into another using deep neural networks, has shown its great power in increasing the message capacity and robustness. In this paper, we conduct an in-depth study of state-of-the-art deep hiding schemes and…

Deepfakes pose severe threats of visual misinformation to our society. One representative deepfake application is face manipulation that modifies a victim's facial attributes in an image, e.g., changing her age or hair color. The…

AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a serious threat,…

Explainable Artificial Intelligence (XAI) strategies play a crucial part in increasing the understanding and trustworthiness of neural networks. Nonetheless, these techniques could potentially generate misleading explanations. Blinding…

Recent advancements in AI-based multimedia generation have enabled the creation of hyper-realistic images and videos, raising concerns about their potential use in spreading misinformation. The widespread accessibility of generative…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Artificial Intelligence (AI) is rapidly integrating into various aspects of our daily lives, influencing decision-making processes in areas such as targeted advertising and matchmaking algorithms. As AI systems become increasingly…

Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We report three findings that challenge…

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…

We introduce the first method, to the best of our knowledge, for adapting image-to-video models to layer-aware text (glyph) animation, a capability critical for practical dynamic visual design. Existing approaches predominantly handle the…

Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VIS-IR) scenarios remains underexplored. This gap is critical because VIS-IR sensing is…

We assess the vulnerabilities of deep face recognition systems for images that falsify/spoof multiple identities simultaneously. We demonstrate that, by manipulating the deep feature representation extracted from a face image via…

The existence of adversarial attacks on convolutional neural networks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked while still looking…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models…

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object.…

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…

The rapid advancement of text-to-image generation systems, exemplified by models like Stable Diffusion, Midjourney, Imagen, and DALL-E, has heightened concerns about their potential misuse. In response, companies like Meta and Google have…

Generative large vision-language models (LVLMs) have recently achieved impressive performance gains, and their user base is growing rapidly. However, the security of LVLMs, in particular in a long-context multi-turn setting, is largely…