相关论文: AdvAnchor: Enhancing Diffusion Model Unlearning wi…

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…

Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches…

Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recent years. Although…

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…

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…

Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which leads to various ethical and business risks. Specifically,…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in the face of adversarial examples. Adversarial examples are…

We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…

Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent…

Anomaly detection is to identify samples that do not conform to the distribution of the normal data. Due to the unavailability of anomalous data, training a supervised deep neural network is a cumbersome task. As such, unsupervised methods…

The recent advances in diffusion models (DMs) have revolutionized the generation of realistic and complex images. However, these models also introduce potential safety hazards, such as producing harmful content and infringing data…

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…

Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts…

We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained…

Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these…

Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Recent research has seen significant interest in methods for concept removal and targeted forgetting in text-to-image diffusion models. In this paper, we conduct a comprehensive white-box analysis showing the vulnerabilities in existing…