More Like this

1. Distribution System Restructuring: Distribution LMP via Unbalanced ACOPF

   https://doi.org/10.1109/TSG.2016.2647692  

   Liu, Yikui; Li, Jie; Wu, Lei (September 2018, IEEE Transactions on Smart Grid)
2. DREAMDISTRIBUTION: LEARNING PROMPT DISTRIBUTION FOR DIVERSE IN-DISTRIBUTION GENERATION

   Zhao, BN; Xiao, Y; Xu, J; Jiang, X; Yang, Y; Li, D; Itti, L; Vineet, V; Ge, Y (April 2025, ICLR 2025)

   The popularization of Text-to-Image (T2I) diffusion models enables the genera- tion of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work focuses on personalizing T2I diffusion models at a more abstract concept or category level, adapting commonalities from a set of reference images while creating new instances with sufficient variations. We introduce a solution that al- lows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution. These prompts offer text-guided editing capabilities and additional flexibility in controlling variation and mixing between multiple distributions. We also show the adaptability of the learned prompt distribution to other tasks, such as text- to-3D. Finally we demonstrate effectiveness of our approach through quantitative analysis including automatic evaluation and human assessment. 

   more » « less
3. In-distribution Equivariance for Conformal Out-of-distribution Detection

   Kaur, R.; Jha, S.; Roy, A.; Park, S.; Dobriban, E.; Sokolsky, O.; Lee I. (January 2022, Proceedings of the AAAI Conference on Artificial Intelligence)
4. Dissecting Distribution Inference

   https://doi.org/10.1109/SaTML54575.2023.00019  

   Suri, Anshuman; Lu, Yifu; Chen, Yanjin; Evans, David (February 2023, IEEE Conference on Secure and Trustworthy Machine Learning (SaTML))
5. Dissecting Distribution Inference.

   https://doi.org/10.1109/SaTML54575.2023.00019  

   Suri, Anshuman; Lu, Yifi; Chen, Yanjin; Evans, David. (December 2022, ArXiv.org. SaTML 2023)

   —A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well understood and demonstrated attacks often rely on strong and unrealistic assumptions such as full knowledge of training environments even in supposedly black-box threat scenarios. To improve understanding of distribution inference risks, we develop a new black-box attack that even outperforms the best known white-box attack in most settings. Using this new attack, we evaluate distribution inference risk while relaxing a variety of assumptions about the adversary’s knowledge under black-box access, like known model architectures and label-only access. Finally, we evaluate the effectiveness of previously proposed defenses and introduce new defenses. We find that although noise-based defenses appear to be ineffective, a simple re-sampling defense can be highly effective. 

   more » « less