相关论文: One Pixel is All I Need

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Recent research has revealed that the output of Deep Neural Networks (DNN) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only…

The unprecedented success of deep neural networks in many applications has made these networks a prime target for adversarial exploitation. In this paper, we introduce a benchmark technique for detecting backdoor attacks (aka Trojan…

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box…

Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV). With the general-purpose Transformer architecture replacing…

Backdoor attacks have been shown to be a serious security threat against deep learning models, and detecting whether a given model has been backdoored becomes a crucial task. Existing defenses are mainly built upon the observation that the…

Vision Transformers (ViTs) have achieved state-of-the-art performance for various vision tasks. One reason behind the success lies in their ability to provide plausible innate explanations for the behavior of neural architectures. However,…

Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks is under-explored. A handful of existing works focus on dirty-label attacks with wrongly-labeled poisoned…

Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack, which embeds…

Vision Transformers (ViTs) are becoming a very popular paradigm for vision tasks as they achieve state-of-the-art performance on image classification. However, although early works implied that this network structure had increased…

Vision Transformers (ViTs) have been widely used in large-scale Vision and Language Pre-training (VLP) models. Though previous VLP works have proved the effectiveness of ViTs, they still suffer from computational efficiency brought by the…

Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training data. However, this way of adversarial injection inevitably…

Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust…

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the efficacy of the…

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…

Keyword spotting (KWS) based on deep neural networks (DNNs) has achieved massive success in voice control scenarios. However, training of such DNN-based KWS systems often requires significant data and hardware resources. Manufacturers often…

Interpretability is crucial to understand the inner workings of deep neural networks (DNNs) and many interpretation methods generate saliency maps that highlight parts of the input image that contribute the most to the prediction made by…

Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack…