Related papers: AdvCLIP: Downstream-agnostic Adversarial Examples …
We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on a variety of audio tasks including classification, retrieval, and…
Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted…
Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data across the two modalities, as exemplified by Contrastive…
Contrastive Language-Image Pretraining (CLIP) has demonstrated strong zero-shot performance across diverse downstream text-image tasks. Existing CLIP methods typically optimize a contrastive objective using negative samples drawn from each…
Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor…
Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful…
Adversarial robustness has been conventionally believed as a challenging property to encode for neural networks, requiring plenty of training data. In the recent paradigm of adopting off-the-shelf models, however, access to their training…
Contrastive vision-language models such as CLIP have demonstrated strong performance across a wide range of multimodal tasks by learning from aligned image-text pairs. However, their ability to handle complex, real-world web documents…
We propose DiffCLIP, a novel vision-language model that extends the differential attention mechanism to CLIP architectures. Differential attention was originally developed for large language models to amplify relevant context while…
Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a…
Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…
Contrastive learning has emerged as an efficient framework to learn multimodal representations. CLIP, a seminal work in this area, achieved impressive results by training on paired image-text data using the contrastive loss. Recent work…
Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of…
With extensive face images being shared on social media, there has been a notable escalation in privacy concerns. In this paper, we propose AdvCloak, an innovative framework for privacy protection using generative models. AdvCloak is…
Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks. More recently, researchers have extended…
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…
The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and system security in…
Universal visual anomaly detection aims to identify anomalies from novel or unseen vision domains without additional fine-tuning, which is critical in open scenarios. Recent studies have demonstrated that pre-trained vision-language models…
Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…
Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…