相关论文: Examining the Threat Landscape: Foundation Models …

Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding. Feature…

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

The increasing realism and accessibility of deepfakes have raised critical concerns about media authenticity and information integrity. Despite recent advances, deepfake detection models often struggle to generalize beyond their training…

Vision transformer (ViT) models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous vehicles, drones,…

Vision classifiers are often trained on proprietary datasets containing sensitive information, yet the models themselves are frequently shared openly under the privacy-preserving assumption. Although these models are assumed to protect…

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

The advent of foundation models (FMs), large-scale pre-trained models with strong generalization capabilities, has opened new frontiers for financial engineering. While general-purpose FMs such as GPT-4 and Gemini have demonstrated…

Although vision foundation models (VFMs) are increasingly reused for biomedical image analysis, it remains unclear whether the latent representations they provide are general enough to support effective transfer and reuse across…

Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…

Masked image modeling (MIM) pre-training for large-scale vision transformers (ViTs) has enabled promising downstream performance on top of the learned self-supervised ViT features. In this paper, we question if the \textit{extremely simple}…

As industrial products become abundant and sophisticated, visual industrial defect detection receives much attention, including two-dimensional and three-dimensional visual feature modeling. Traditional methods use statistical analysis,…

Recently, several studies have reported on the fine-tuning of foundation models for image-text modeling in the field of medicine, utilizing images from online data sources such as Twitter and PubMed. Foundation models are large, deep…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

Image scaling is an integral part of machine learning and computer vision systems. Unfortunately, this preprocessing step is vulnerable to so-called image-scaling attacks where an attacker makes unnoticeable changes to an image so that it…

The rapid development of Vision Foundation Models (VFMs), particularly Vision Transformers (ViT) and Segment Anything Model (SAM), has sparked significant advances in the field of medical image analysis. These models have demonstrated…

Foundation models have recently emerged as a new paradigm in machine learning (ML). These models are pre-trained on large and diverse datasets and can subsequently be applied to various downstream tasks with little or no retraining. This…

Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote sensing, where data acquisition is costly and annotation often…

Recent advances in biometric systems have significantly improved the detection and prevention of fraudulent activities. However, as detection methods improve, attack techniques become increasingly sophisticated. Attacks on face recognition…

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Segment Anything Model (SAM) has attracted significant attention recently, due to its impressive performance on various downstream tasks in a zero-short manner. Computer vision (CV) area might follow the natural language processing (NLP)…