Related papers: LiteGuard: Efficient Task-Agnostic Model Fingerpri…

Protecting the intellectual property of large language models requires robust ownership verification. Conventional backdoor fingerprinting, however, is flawed by a stealth-robustness paradox: to be robust, these methods force models to…

The rapidly evolving industry demands high accuracy of the models without the need for time-consuming and computationally expensive experiments required for fine-tuning. Moreover, a model and training pipeline, which was once carefully…

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate…

Meta-learning algorithms enable rapid adaptation to new tasks with minimal data, a critical capability for real-world robotic systems. This paper evaluates Model-Agnostic Meta-Learning (MAML) combined with Trust Region Policy Optimization…

The study of security in machine learning mainly focuses on downstream task-specific attacks, where the adversarial example is obtained by optimizing a loss function specific to the downstream task. At the same time, it has become standard…

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional…

Identification of suspects based on partial and smudged fingerprints, commonly referred to as fingermarks or latent fingerprints, presents a significant challenge in the field of fingerprint recognition. Although fixed-length embeddings…

Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. While AT has been extensively studied, its practical…

Achieving state-of-the-art performance on natural language understanding tasks typically relies on fine-tuning a fresh model for every task. Consequently, this approach leads to a higher overall parameter cost, along with higher technical…

Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating…

Face presentation attacks have become an increasingly critical concern when face recognition is widely applied. Many face anti-spoofing methods have been proposed, but most of them ignore the generalization ability to unseen attacks. To…

Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a…

Pre-trained vision-language models have shown impressive success on various computer vision tasks with their zero-shot generalizability. Recently, prompt learning approaches have been explored to efficiently and effectively adapt the…

Biometric authentication systems are increasingly being deployed in critical applications, but they remain susceptible to spoofing. Since most of the research efforts focus on modality-specific anti-spoofing techniques, building a unified,…

Recently, Vision Transformers (ViTs) have achieved unprecedented effectiveness in the general domain of image classification. Nonetheless, these models remain underexplored in the field of deepfake detection, given their lower performance…

Self-supervised pre-training of transformer models has shown enormous success in improving performance on a number of downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labelled data to…

The use of transformers for vision tasks has challenged the traditional dominant role of convolutional neural networks (CNN) in computer vision (CV). For image classification tasks, Vision Transformer (ViT) effectively establishes spatial…

The rapid growth of machine learning has produced an ever-expanding ecosystem of models, making it increasingly challenging to verify the reliability of newly released models on unseen, unlabeled data. Conventional evaluation pipelines…

Foundation models such as CLIP have demonstrated exceptional zero- and few-shot transfer capabilities across diverse vision tasks. However, when fine-tuned for highly specialized biometric tasks, face recognition (FR), morphing attack…

In the web era, graph machine learning has been widely used on ubiquitous graph-structured data. As a pivotal component for bolstering web security and enhancing the robustness of graph-based applications, the significance of graph anomaly…