Related papers: UniShield: Unified Face Attack Detection via KG-In…

Audio plays a crucial role in applications like speaker verification, voice-enabled smart devices, and audio conferencing. However, audio manipulations, such as deepfakes, pose significant risks by enabling the spread of misinformation. Our…

The rapid advancement of AI-generation models has enabled the creation of hyperrealistic imagery, posing ethical risks through widespread misinformation. Current deepfake detection methods, categorized as face specific detectors or general…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Recent research on the robustness of Graph Neural Networks (GNNs) under noises or attacks has attracted great attention due to its importance in real-world applications. Most previous methods explore a single noise source, recovering…

CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models'…

We have witnessed rapid advances in both face presentation attack models and presentation attack detection (PAD) in recent years. When compared with widely studied 2D face presentation attacks, 3D face spoofing attacks are more challenging…

Infrared unmanned aerial vehicle (UAV) images captured using thermal detectors are often affected by temperature dependent low-frequency nonuniformity, which significantly reduces the contrast of the images. Detecting UAV targets under…

The success of graph neural networks stimulates the prosperity of graph mining and the corresponding downstream tasks including graph anomaly detection (GAD). However, it has been explored that those graph mining methods are vulnerable to…

The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively. Even though the convolutional neural network and generative adversarial network-based methods deliver…

Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardrail research largely targets unimodal settings and typically…

Generalizing to unseen graph tasks without task-specific supervision is challenging: conventional graph neural networks are typically tied to a fixed label space, while large language models (LLMs) struggle to capture graph structure. We…

Unsupervised object discovery (UOD) aims to detect and segment objects in 2D images without handcrafted annotations. Recent progress in self-supervised representation learning has led to some success in UOD algorithms. However, the absence…

Generative AI, such as Large Language Models (LLMs), has achieved impressive progress but still produces hallucinations and unverifiable claims, limiting reliability in sensitive domains. Retrieval-Augmented Generation (RAG) improves…

Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various…

Corporate AI-washing-the strategic misrepresentation of AI capabilities via exaggerated or fabricated cross-channel disclosures-has emerged as a systemic threat to capital market information integrity with the widespread adoption of…

We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose estimation, and different frameworks, such as one-stage or…

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision-making,…

Graph neural networks (GNNs) have achieved remarkable success in relational learning. However, their vulnerability to graph backdoor attacks (GBAs) poses a significant barrier to broader adoption in high-stakes applications. Despite recent…

Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing…

Multimodal retrieval methods have limitations in handling complex, compositional queries that require reasoning about the visual content of both the query and the retrieved entities. On the other hand, Large Multimodal Models (LMMs) can…