相关论文: ME: Trigger Element Combination Backdoor Attack on…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Recently, stable diffusion (SD) models have typically flourished in the field of image synthesis and personalized editing, with a range of photorealistic and unprecedented images being successfully generated. As a result, widespread…

Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarkable attack effects…

The fine-tuning technique for text-to-image diffusion models facilitates image customization but risks privacy breaches and opinion manipulation. Current research focuses on prompt- or image-level adversarial attacks for anti-customization,…

Diffusion models have achieved great success in a range of tasks, such as image synthesis and molecule design. As such successes hinge on large-scale training data collected from diverse sources, the trustworthiness of these collected data…

Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These…

Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study the problem of adversarial attack generation for Stable…

Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows, making them the focus in recent years. Despite their remarkable capability to generate…

Diffusion models are powerful generative models in continuous data domains such as image and video data. Discrete graph diffusion models (DGDMs) have recently extended them for graph generation, which are crucial in fields like molecule and…

With advances in diffusion models, image generation has shown significant performance improvements. This raises concerns about the potential abuse of image generation, such as the creation of explicit or violent images, commonly referred to…

Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vulnerability to backdoor attacks. Existing attack methods…

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are…

In recent years, diffusion models have achieved tremendous success in the field of image generation, becoming the stateof-the-art technology for AI-based image processing applications. Despite the numerous benefits brought by recent…

Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations…

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they…

Intrusion Detection Systems (IDSs) are a key component for protecting Internet of Things (IoT) environments. However, in Machine Learning-based (ML-based) IDSs, performance is often degraded by the strong class imbalance between benign and…

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such…

Since the training data of the target model is not available in the black-box substitute attack, most recent schemes utilize GANs to generate data for training the substitute model. However, these GANs-based schemes suffer from low training…