152 citations · 379 across the 19 of their papers we have counts for
19 papers
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Xindi Wu, Dingli Yu, Yangsibo Huang +2
Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing e…
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Yangsibo Huang, Samyak Gupta, Mengzhou Xia +2
The rapid progress in open-source large language models (LLMs) is significantly advancing AI development. Extensive efforts have been made before model release to align their behav…
Detecting Pretraining Data from Large Language Models
Weijia Shi, Anirudh Ajith, Mengzhou Xia +5
Although large language models (LLMs) are widely deployed, the data used to train them is rarely disclosed. Given the incredible scale of this data, up to trillions of tokens, it i…
Learning across Data Owners with Joint Differential Privacy
Yangsibo Huang, Haotian Jiang, Daogao Liu +3
In this paper, we study the setting in which data owners train machine learning models collaboratively under a privacy notion called joint differential privacy [Kearns et al., 2018…
Privacy Implications of Retrieval-Based Language Models
Yangsibo Huang, Samyak Gupta, Zexuan Zhong +2
Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts, by incorporating retrieve…
GMValuator: Similarity-based Data Valuation for Generative Models
Jiaxi Yang, Wenglong Deng, Benlin Liu +3
Data valuation plays a crucial role in machine learning. Existing data valuation methods, mainly focused on discriminative models, overlook generative models that have gained atten…
Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Rachel Cummings, Damien Desfontaines, David Evans +21
In this article, we present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP), with a focus of advancing DP's depl…
NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
Yangsibo Huang, Daogao Liu, Zexuan Zhong +2
Fine-tuning a language model on a new domain is standard practice for domain adaptation. However, it can be infeasible when it comes to modern large-scale language models such as G…
Recovering Private Text in Federated Learning of Language Models
Samyak Gupta, Yangsibo Huang, Zexuan Zhong +3
Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eaves…
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning
Yangsibo Huang, Samyak Gupta, Zhao Song +2
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or…
EMA: Auditing Data Removal from Trained Models
Yangsibo Huang, Xiaoxiao Li, Kai Li
Data auditing is a process to verify whether certain data have been removed from a trained model. A recently proposed method (Liu et al. 20) uses Kolmogorov-Smirnov (KS) distance f…
IFGAN: Missing Value Imputation using Feature-specific Generative Adversarial Networks
Wei Qiu, Yangsibo Huang, Quanzheng Li
Missing value imputation is a challenging and well-researched topic in data mining. In this paper, we propose IFGAN, a missing value imputation algorithm based on Feature-specific…
MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
Xiaoxiao Li, Yangsibo Huang, Binghui Peng +2
To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data…
TextHide: Tackling Data Privacy in Language Understanding Tasks
Yangsibo Huang, Zhao Song, Danqi Chen +2
An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose Te…
InstaHide: Instance-hiding Schemes for Private Distributed Learning
Yangsibo Huang, Zhao Song, Kai Li +1
How can multiple distributed entities collaboratively train a shared deep net on their private data while preserving privacy? This paper introduces InstaHide, a simple encryption o…
Deep Learning Based Detection and Localization of Intracranial Aneurysms in Computed Tomography Angiography
Dufan Wu, Daniel Montes, Ziheng Duan +4
Purpose: To develop CADIA, a supervised deep learning model based on a region proposal network coupled with a false-positive reduction module for the detection and localization of…
Privacy-preserving Learning via Deep Net Pruning
Yangsibo Huang, Yushan Su, Sachin Ravi +3
This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility. As a first step to…
DeepMCDose: A Deep Learning Method for Efficient Monte Carlo Beamlet Dose Calculation by Predictive Denoising in MR-Guided Radiotherapy
Ryan Neph, Yangsibo Huang, Youming Yang +1
The next great leap toward improving treatment of cancer with radiation will require the combined use of online adaptive and magnetic resonance guided radiation therapy techniques…
Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net
Yunze Man, Yangsibo Huang, Junyi Feng +2
Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features. To a…