相关论文: Adversarial Robustness for Unified Multi-Modal Enc…

Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challenges in real-world queries and targets involving diverse modality combinations, as existing…

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions,…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

The robustness of Vision-Language Models (VLMs) such as CLIP is critical for their deployment in safety-critical applications like autonomous driving, healthcare diagnostics, and security systems, where accurate interpretation of visual and…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical analysis suggesting that adversarially pretrained transformers…

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs)…

Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single…

Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this…

Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of…

Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images can be slightly…

Transformer-based language models for code have shown remarkable performance in various software analytics tasks, but their adoption is hindered by high computational costs, slow inference speeds, and substantial environmental impact. Model…

Different from a unimodal model whose input is from a single modality, the input (called multi-modal input) of a multi-modal model is from multiple modalities such as image, 3D points, audio, text, etc. Similar to unimodal models, many…

To overcome the imbalanced multimodal learning problem, where models prefer the training of specific modalities, existing methods propose to control the training of uni-modal encoders from different perspectives, taking the inter-modal…

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

The field of adversarial robustness has attracted significant attention in machine learning. Contrary to the common approach of training models that are accurate in average case, it aims at training models that are accurate for worst case…