相关论文: Mitigating Sexual Content Generation via Embedding…

Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks. Whereas…

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…

Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suffer from overfitting issues and entangle the…

Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. Although prior studies have explored the vulnerability of diffusion models from the…

Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character identity across diverse scene descriptions remains a…

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…

Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…

This paper concerns corpus poisoning attacks in dense information retrieval, where an adversary attempts to compromise the ranking performance of a search algorithm by injecting a small number of maliciously generated documents into the…

The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnerabilities of these solutions are underexplored. In this…

Multi-modal foundation models align images, text, and other modalities in a shared embedding space but remain vulnerable to adversarial illusions [35], where imperceptible perturbations disrupt cross-modal alignment and mislead downstream…

While text-driven diffusion models demonstrate remarkable performance in image editing, the critical components of their text embeddings remain underexplored. The ambiguity and entanglement of these embeddings pose challenges for precise…

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remove or filter…

Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity. While previous approaches like DreamBooth…

Text-to-image (T2I) models have demonstrated remarkable generative capabilities but remain vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery. While recent moderation efforts have introduced soft…

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…

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

Motivated by ethical and legal concerns, the scientific community is actively developing methods to limit the misuse of Text-to-Image diffusion models for reproducing copyrighted, violent, explicit, or personal information in the generated…

Diffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific undesirable outputs when presented with a pre-defined trigger.…

Robust invisible watermarking aims to embed hidden messages into images such that they survive various manipulations while remaining imperceptible. However, powerful diffusion-based image generation and editing models now enable realistic…

There is growing concern over the safety of powerful diffusion models (DMs), as they are often misused to produce inappropriate, not-safe-for-work (NSFW) content or generate copyrighted material or data of individuals who wish to be…