相关论文: No Safe Dose: How Training Data Drives Unsafe Imag…

Text-to-image generation requires large amount of training data to synthesizing high-quality images. For augmenting training data, previous methods rely on data interpolations like cropping, flipping, and mixing up, which fail to introduce…

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially…

Recent advancements in text-to-image (T2I) models have unlocked a wide range of applications but also present significant risks, particularly in their potential to generate unsafe content. To mitigate this issue, researchers have developed…

Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image…

Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether…

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…

Advances in brain decoding, particularly visual image reconstruction, have sparked discussions about the societal implications and ethical considerations of neurotechnology. As these methods aim to recover visual experiences from brain…

The rise of deep learning models in the digital era has raised substantial concerns regarding the generation of Not-Safe-for-Work (NSFW) content. Existing defense methods primarily involve model fine-tuning and post-hoc content moderation.…

Text-to-image diffusion models have achieved widespread popularity due to their unprecedented image generation capability. In particular, their ability to synthesize and modify human faces has spurred research into using generated face…

We propose a new strategy to improve the accuracy and robustness of image classification. First, we train a baseline CNN model. Then, we identify challenging regions in the feature space by identifying all misclassified samples, and…

Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a…

When data is generated by multiple sources, conventional training methods update models assuming equal reliability for each source and do not consider their individual data quality. However, in many applications, sources have varied levels…

Large language models write production code, and yet they routinely introduce well-known vulnerabilities. We show that this is not a knowledge deficit: the same models that generate insecure code, correctly identify and explain the…

Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual text prompts and…

Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without…

Text-to-image diffusion-based generative models have the stunning ability to generate photo-realistic images and achieve state-of-the-art low FID scores on challenging image generation benchmarks. However, one of the primary failure modes…

When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as…

Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding of poisoning attacks…

Image classifiers should be used with caution in the real world. Performance evaluated on a validation set may not reflect performance in the real world. In particular, classifiers may perform well for conditions that are frequently…

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,…