Related papers: Open-World Deepfake Attribution via Confidence-Awa…

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i.e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative…

Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training. However, the problem remains challenging when one tries to generalize the detector to forgeries from…

A major challenge in DeepFake forgery detection is that state-of-the-art algorithms are mostly trained to detect a specific fake method. As a result, these approaches show poor generalization across different types of facial manipulations,…

The surge in face forgeries has increasingly undermined confidence in the authenticity of online content. As generation algorithms rapidly evolve, new fake categories will constantly emerge, severely challenging existing face forgery…

Recently, self-attention mechanisms have shown impressive performance in various NLP and CV tasks, which can help capture sequential characteristics and derive global information. In this work, we explore how to extend self-attention…

Image forgery detection aims to detect and locate forged regions in an image. Most existing forgery detection algorithms formulate classification problems to classify pixels into forged or pristine. However, the definition of forged and…

A major challenge that prevents the training of DL models is the limited availability of accurately labeled data. This shortcoming is highlighted in areas where data annotation becomes a time-consuming and error-prone task. In this regard,…

In recent years, deep neural networks (DNNs) have shown competitive results in many fields. Despite this success, they often suffer from poor calibration, especially in safety-critical scenarios such as autonomous driving and healthcare,…

Existing face forgery detection methods usually treat face forgery detection as a binary classification problem and adopt deep convolution neural networks to learn discriminative features. The ideal discriminative features should be only…

Modern deepfakes have evolved into localized and intermittent manipulations that require fine-grained temporal localization to mitigate severe digital security risks. The prohibitive cost of frame-level annotation makes weakly supervised…

Facial manipulation by deep fake has caused major security risks and raised severe societal concerns. As a countermeasure, a number of deep fake detection methods have been proposed recently. Most of them model deep fake detection as a…

As speech synthesis systems continue to make remarkable advances in recent years, the importance of robust deepfake detection systems that perform well in unseen systems has grown. In this paper, we propose a novel adaptive centroid shift…

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

Existing deepfake detection techniques struggle to keep-up with the ever-evolving novel, unseen forgeries methods. This limitation stems from their reliance on statistical artifacts learned during training, which are often tied to specific…

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…

Achieving robust generalization against unseen attacks remains a challenge in Audio Deepfake Detection (ADD), driven by the rapid evolution of generative models. To address this, we propose a framework centered on hard sample…

The deployment of multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address…

The rapid proliferation of highly realistic AI-generated images poses serious security threats such as misinformation and identity fraud. Detecting generated images in open-world settings is particularly challenging when they originate from…

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They…