no code implementations • 18 Apr 2024 • Lixing Tan, Shuang Song, Kangneng Zhou, Chengbo Duan, Lanying Wang, Huayang Ren, Linlin Liu, Wei zhang, Ruoxiu Xiao
Meanwhile, we also impose a supervised process by computing the similarity of computed real DRR and synthesized DRR images.
no code implementations • 1 Apr 2024 • Shuang Song
3D scene modeling techniques serve as the bedrocks in the geospatial engineering and computer science, which drives many applications ranging from automated driving, terrain mapping, navigation, virtual, augmented, mixed, and extended reality (for gaming and movie industry etc.).
no code implementations • 18 Mar 2024 • Yue Ding, Hongqiao Shi, Shuang Song, Yonghui Wang, Ya Li
The integration of local elements into shape contours is critical for target detection and identification in cluttered scenes.
no code implementations • 24 Oct 2023 • Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
We study a class of private learning problems in which the data is a join of private and public features.
1 code implementation • ICCV 2023 • Shuang Song, Yuanbang Liang, Jing Wu, Yu-Kun Lai, Yipeng Qin
Thanks to our discovery of Feature Proliferation, the proposed feature rescaling method is less destructive and retains more useful image features than the truncation trick, as it is more fine-grained and works in a lower-level feature space rather than a high-level latent space.
no code implementations • 23 Aug 2023 • Shuang Song, Rongjun Qin
Conflating/stitching 2. 5D raster digital surface models (DSM) into a large one has been a running practice in geoscience applications, however, conflating full-3D mesh models, such as those from oblique photogrammetry, is extremely challenging.
no code implementations • 15 Feb 2023 • Walid Krichene, Prateek Jain, Shuang Song, Mukund Sundararajan, Abhradeep Thakurta, Li Zhang
We study the problem of multi-task learning under user-level differential privacy, in which $n$ users contribute data to $m$ tasks, each involving a subset of users.
1 code implementation • 14 Feb 2023 • Ningli Xu, Rongjun Qin, Shuang Song
In this work, we provide a comprehensive review of the state-of-the-art (SOTA) point cloud registration methods, where we analyze and evaluate these methods using a diverse set of point cloud data from indoor to satellite sources.
no code implementations • 30 Jun 2022 • Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Chiyuan Zhang
In memorization, models overfit specific training examples and become susceptible to privacy attacks.
no code implementations • 8 Apr 2022 • Shuang Song, Rongjun Qin
Recovering surface albedos from photogrammetric images for realistic rendering and synthetic environments can greatly facilitate its downstream applications in VR/AR/MR and digital twins.
no code implementations • 24 Feb 2022 • Florian Tramer, Andreas Terzis, Thomas Steinke, Shuang Song, Matthew Jagielski, Nicholas Carlini
Differential Privacy can provide provable privacy guarantees for training data in machine learning.
1 code implementation • 28 Jan 2022 • Alexey Kurakin, Shuang Song, Steve Chien, Roxana Geambasu, Andreas Terzis, Abhradeep Thakurta
Despite a rich literature on how to train ML models with differential privacy, it remains extremely challenging to train real-life, large neural networks with both reasonable accuracy and privacy.
2 code implementations • 7 Dec 2021 • Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, Florian Tramer
A membership inference attack allows an adversary to query a trained machine learning model to predict whether or not a particular example was contained in the model's training dataset.
no code implementations • 2 Dec 2021 • Jingyi Feng, Yong Luo, Shuang Song
Neural decoding plays a vital role in the interaction between the brain and the outside world.
no code implementations • 1 Dec 2021 • Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
In this paper, we revisit the problem of using in-distribution public data to improve the privacy/utility trade-offs for differentially private (DP) model training.
no code implementations • NeurIPS 2021 • Prateek Jain, John Rush, Adam Smith, Shuang Song, Abhradeep Guha Thakurta
We study personalization of supervised learning with user-level differential privacy.
1 code implementation • ICCV 2021 • Shuang Song, Zhaopeng Cui, Rongjun Qin
Then the visibility information of multiple views is aggregated to generate a 3D mesh model by solving an optimization problem considering visibility in which a novel adaptive visibility weighting in surface determination is also introduced to suppress line of sight with a large incident angle.
no code implementations • 5 Aug 2021 • Ningli Xu, Debao Huang, Shuang Song, Xiao Ling, Chris Strasbaugh, Alper Yilmaz, Halil Sezen, Rongjun Qin
In this paper, we present a case study that performs an unmanned aerial vehicle (UAV) based fine-scale 3D change detection and monitoring of progressive collapse performance of a building during a demolition event.
no code implementations • 20 Jul 2021 • Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
We study the problem of differentially private (DP) matrix completion under user-level privacy.
no code implementations • 27 Jun 2021 • Rongjun Qin, Shuang Song, Xiao Ling, Mostafa Elhashash
3D recovery from multi-stereo and stereo images, as an important application of the image-based perspective geometry, serves many applications in computer vision, remote sensing and Geomatics.
2 code implementations • 26 Feb 2021 • Peter Kairouz, Brendan Mcmahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu
We consider training models with differential privacy (DP) using mini-batch gradients.
no code implementations • 11 Jan 2021 • Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a dataset D, or a dataset D' that differs in just one example. If observing the training algorithm does not meaningfully increase the adversary's odds of successfully guessing which dataset the model was trained on, then the algorithm is said to be differentially private.
no code implementations • NeurIPS 2020 • Adam Smith, Shuang Song, Abhradeep Thakurta
We propose an $(\epsilon,\delta)$-differentially private algorithm that approximates $\dist$ within a factor of $(1\pm\gamma)$, and with additive error of $O(\sqrt{\ln(1/\delta)}/\epsilon)$, using space $O(\ln(\ln(u)/\gamma)/\gamma^2)$.
2 code implementations • 10 Nov 2020 • Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramer
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy.
1 code implementation • 28 Jul 2020 • Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson
Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer privacy for training data.
no code implementations • 11 Jun 2020 • Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta
We show that for unconstrained convex generalized linear models (GLMs), one can obtain an excess empirical risk of $\tilde O\left(\sqrt{{\texttt{rank}}}/\epsilon n\right)$, where ${\texttt{rank}}$ is the rank of the feature matrix in the GLM problem, $n$ is the number of data samples, and $\epsilon$ is the privacy parameter.
1 code implementation • 2 Dec 2019 • Shuang Song, David Berthelot, Afshin Rostamizadeh
This analysis can be used to measure the relative value of labeled/unlabeled data at different points of the learning curve, where we find that although the incremental value of labeled data can be as much as 20x that of unlabeled, it quickly diminishes to less than 3x once more than 2, 000 labeled example are observed.
no code implementations • 25 Sep 2019 • Nicolas Papernot, Steve Chien, Shuang Song, Abhradeep Thakurta, Ulfar Erlingsson
Because learning sometimes involves sensitive data, standard machine-learning algorithms have been extended to offer strong privacy guarantees for training data.
no code implementations • 8 Aug 2019 • Úlfar Erlingsson, Ilya Mironov, Ananth Raghunathan, Shuang Song
Instead, the definitions so named are the basis of refinements and more advanced analyses of the worst-case implications of attackers---without any change assumed in attackers' powers.
no code implementations • 22 May 2019 • Bihe Chen, Rongjun Qin, Xu Huang, Shuang Song, Xiaohu Lu
Stereo dense image matching can be categorized to low-level feature based matching and deep feature based matching according to their matching cost metrics.
3 code implementations • ICLR 2018 • Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Úlfar Erlingsson
Models and examples built with TensorFlow
no code implementations • NeurIPS 2017 • Joseph Geumlek, Shuang Song, Kamalika Chaudhuri
With the newly proposed privacy definition of Rényi Differential Privacy (RDP) in (Mironov, 2017), we re-examine the inherent privacy of releasing a single sample from a posterior distribution.
no code implementations • 2 Oct 2017 • Joseph Geumlek, Shuang Song, Kamalika Chaudhuri
Using a recently proposed privacy definition of R\'enyi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution.
no code implementations • 10 Jul 2017 • Shuang Song, Kamalika Chaudhuri
With the proliferation of mobile devices and the internet of things, developing principled solutions for privacy in time series applications has become increasingly important.
no code implementations • 13 Mar 2016 • Shuang Song, Yizhen Wang, Kamalika Chaudhuri
Since this mechanism may be computationally inefficient, we provide an additional mechanism that applies to some practical cases such as physical activity measurements across time, and is computationally efficient.
no code implementations • 17 Dec 2014 • Shuang Song, Kamalika Chaudhuri, Anand D. Sarwate
In this paper, we adopt instead a model in which data is observed through heterogeneous noise, where the noise level reflects the quality of the data source.
no code implementations • NeurIPS 2014 • Kamalika Chaudhuri, Daniel Hsu, Shuang Song
A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a data-dependent function, all under the constraint of differential privacy.