相关论文: Defending Multimodal Fusion Models against Single-…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative effect, in this paper, we investigate the dependence between…

Standard multi-modal models assume the use of the same modalities in training and inference stages. However, in practice, the environment in which multi-modal models operate may not satisfy such assumption. As such, their performances…

When data is generated by multiple sources, conventional training methods update models assuming equal reliability for each source and do not consider their individual data quality. However, in many applications, sources have varied levels…

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Recently, there have been numerous studies on feature learning with neural networks, specifically on learning single- and multi-index models where the target is a function of a low-dimensional projection of the input. Prior works have shown…

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We…

Neural machine translation (NMT) often suffers from the vulnerability to noisy perturbations in the input. We propose an approach to improving the robustness of NMT models, which consists of two parts: (1) attack the translation model with…

Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the…

Although many fields have witnessed the superior performance brought about by deep learning, the robustness of neural networks remains an open issue. Specifically, a small adversarial perturbation on the input may cause the model to produce…

Multimodal learning integrates information from different modalities to enhance model performance, yet it often suffers from modality imbalance, where dominant modalities overshadow weaker ones during joint optimization. This paper reveals…

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliability and robustness of deep neural network models is crucial…

Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require…

Multimodal learning systems often encounter challenges related to modality imbalance, where a dominant modality may overshadow others, thereby hindering the learning of weak modalities. Conventional approaches often force weak modalities to…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing…

Diffusion models have gained significant attention for high-fidelity image generation. Our work investigates the potential of exploiting diffusion models for adversarial robustness in image classification and object detection. Adversarial…

Adversarial robustness of deep neural networks has been actively investigated. However, most existing defense approaches are limited to a specific type of adversarial perturbations. Specifically, they often fail to offer resistance to…