相关论文: Robustness in Both Domains: CLIP Needs a Robust Te…

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…

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…

Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning…

Pre-trained large models for multimodal contrastive learning, such as CLIP, have been widely recognized in the industry as highly susceptible to data-poisoned backdoor attacks. This poses significant risks to downstream model training. In…

This work addresses the challenge of achieving zero-shot adversarial robustness while preserving zero-shot generalization in large-scale foundation models, with a focus on the popular Contrastive Language-Image Pre-training (CLIP). Although…

The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…

Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model jailbreaks. In this work, we analyze how CLIP vision encoders…

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit various complex downstream tasks, including cross-modal…

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We show that this approach significantly improves robustness…

Large-scale vision-language models demonstrate strong multimodal alignment and generalization across diverse tasks. Among them, CLIP stands out as one of the most successful approaches. In this work, we extend the application of CLIP to…

Contrastive Language-Image Pretraining (CLIP) achieves strong generalization in vision-language tasks by aligning images and texts in a shared embedding space. However, recent findings show that CLIP-like models still underutilize…

This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo. Our approach is based on developing an extension for the conventional distortion condition…

Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed…

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language…

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature…

With contrastive pre-training, sentence encoders are generally optimized to locate semantically similar samples closer to each other in their embedding spaces. In this work, we focus on the potential of their embedding spaces to be readily…

Previous works show that noisy, web-crawled image-text pairs may limit vision-language pretraining like CLIP and propose learning with synthetic captions as a promising alternative. Our work continues this effort, introducing two simple yet…

Recent advances in vision-language models (VLMs) trained on web-scale image-text pairs have enabled impressive zero-shot transfer across a diverse range of visual tasks. However, comprehensive and independent evaluation beyond standard…

Recent research has shown that CLIP models struggle with visual reasoning tasks that require grounding compositionality, understanding spatial relationships, or capturing fine-grained details. One natural hypothesis is that the CLIP vision…