相关论文: PEPPER: Perception-Guided Perturbation for Robust …

Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest of the image. Although diffusion models have been shown to…

We investigate a new threat to neural sequence-to-sequence (seq2seq) models: training-time attacks that cause models to "spin" their output and support a certain sentiment when the input contains adversary-chosen trigger words. For example,…

Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images…

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Text-to-Image (T2I) models, represented by DALL$\cdot$E and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the carefully engineered prompts, which have become valuable…

As text-to-image diffusion models become increasingly deployed in real-world applications, concerns about backdoor attacks have gained significant attention. Prior work on text-based backdoor attacks has largely focused on diffusion models…

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security threats associated…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

In the last two years, text-to-image diffusion models have become extremely popular. As their quality and usage increase, a major concern has been the need for better output control. In addition to prompt engineering, one effective method…

Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs when specific triggers are present. While classification…

The success of recent text-to-image diffusion models is largely due to their capacity to be guided by a complex text prompt, which enables users to precisely describe the desired content. However, these models struggle to effectively…

With the open-sourcing of text-to-image models (T2I) such as stable diffusion (SD) and stable diffusion XL (SD-XL), there is an influx of models fine-tuned in specific domains based on the open-source SD model, such as in anime, character…

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Recent advancements in Text-to-Image (T2I) diffusion models have demonstrated impressive success in generating high-quality images with zero-shot generalization capabilities. Yet, current models struggle to closely adhere to prompt…

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as DALL-E, Stable Diffusion, Imagen, etc. In practice, it has…

Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are impractical since visually embedded triggers rarely occur in real-world data. To overcome this…

Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts.…