相关论文: Boosting Adversarial Transferability via Ensemble …

Adversarial attacks have rendered high security risks on modern deep learning systems. Adversarial training can significantly enhance the robustness of neural network models by suppressing the non-robust features. However, the models often…

Given the wide and ever growing range of different efficient Transformer attention mechanisms, it is important to identify which attention is most effective when given a task. In this work, we are also interested in combining different…

The spread of deepfakes poses significant security concerns, demanding reliable detection methods. However, diverse generation techniques and class imbalance in datasets create challenges. We propose CAE-Net, a Convolution- and…

Adversarial attacks on tabular data present unique challenges due to the heterogeneous nature of mixed categorical and numerical features. Unlike images where pixel perturbations maintain visual similarity, tabular data lacks intuitive…

In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN). First, our approach transfers knowledge in all the convolutional layers through attention alignment. Most…

Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples generated from surrogate models often exhibit weak…

Learning solution operators for systems with complex, varying geometries and parametric physical settings is a central challenge in scientific machine learning. In many-query regimes such as design optimization, control and inverse…

In healthcare, medical image segmentation is crucial for accurate disease diagnosis and the development of effective treatment strategies. Early detection can significantly aid in managing diseases and potentially prevent their progression.…

Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification performance on natural examples), we investigate and identify…

Ensemble-based adversarial training is a principled approach to achieve robustness against adversarial attacks. An important technique of this approach is to control the transferability of adversarial examples among ensemble members. We…

Neural network models that are not conditioned on class identities were shown to facilitate knowledge transfer between classes and to be well-suited for one-shot learning tasks. Following this motivation, we further explore and establish…

The favorable performance of Vision Transformers (ViTs) is often attributed to the multi-head self-attention (MSA). The MSA enables global interactions at each layer of a ViT model, which is a contrasting feature against Convolutional…

While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attacks are one of the effective attack types, which targets the…

Recently, self-attention operators have shown superior performance as a stand-alone building block for vision models. However, existing self-attention models are often hand-designed, modified from CNNs, and obtained by stacking one operator…

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency to memorize training data raises serious privacy and…

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model…

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…

This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple universal perturbation can fool a series of state-of-the-art…

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…