相关论文: Adversarial Robustification via Text-to-Image Diff…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning. The main objective is twofold: first, to evaluate the robustness of CLIP, and…

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on…

Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often…

Despite their great success, deep neural networks rely on high-dimensional, non-robust representations, making them vulnerable to imperceptible perturbations, even in transfer scenarios. To address this, both training-time defenses (e.g.,…

Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise, their susceptibility to out-of-distribution (OOD)…

Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms have been proposed to make neural networks robust to…

Deep learning methods have achieved great success in solving computer vision tasks, and they have been widely utilized in artificially intelligent systems for image processing, analysis, and understanding. However, deep neural networks have…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…

Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervised weight edits or global penalties; reinforcement-learning…

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…

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this paper, we strive to explore the robust features…

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…

CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves as the backbone of many generative pipelines, where a decoder is trained to map from the shared space…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

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…

In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image with text prompts ``a…

Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against these attacks, most existing methods apply adversarial training…