相关论文: From Feature Visualization to Visual Circuits: Eff…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

The visual pathway involves complex networks of cells and regions which contribute to the encoding and processing of visual information. While some aspects of visual perception are understood, there are still many unanswered questions…

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating…

Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of product images extracted from a deep neural network (DNN). Recently, human-imperceptible images…

Human observers engage in selective information uptake when classifying visual patterns. The same is true of deep neural networks, which currently constitute the best performing artificial vision systems. Our goal is to examine the…

The study of mechanistic interpretability aims to reverse-engineer a model to explain its behaviors. While recent studies have focused on the static mechanism of a certain behavior, the learning dynamics inside a model remain to be…

High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this…

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the understanding and mitigation of adversarial attacks. FACADE…

The field of deep learning is evolving in different directions, with still the need for more efficient training strategies. In this work, we present a novel and robust training scheme that integrates visual explanation techniques in the…

We introduce a novel artificial neural network architecture that integrates robustness to adversarial input in the network structure. The main idea of our approach is to force the network to make predictions on what the given instance of…

Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications. Existing ViT adversarial attackers rely on la…

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to…

Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to…

Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical…

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal…

Vision Transformers (ViTs) have a radically different architecture with significantly less inductive bias than Convolutional Neural Networks. Along with the improvement in performance, security and robustness of ViTs are also of great…

Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional…