Search Results for author: Chuan Guo

Found 74 papers, 44 papers with code

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks

1 code implementation3 Jul 2025 Sizhe Chen, Arman Zharmagambetov, David Wagner, Chuan Guo

We believe open-source models are needed by the AI security community, where co-development of attacks and defenses through open research drives scientific progress in mitigation against prompt injection attacks.

Instruction Following

Machine Learning with Privacy for Protected Attributes

no code implementations24 Jun 2025 Saeed Mahloujifar, Chuan Guo, G. Edward Suh, Kamalika Chaudhuri

For example, we train diffusion models on the AFHQ dataset of animal faces and observe a drastic improvement in FID compared to DP, from 286. 7 to 101. 9 at $\epsilon=8$, assuming that the blurred version of a training image is available as a public feature.

Attribute

DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling

1 code implementation23 Jun 2025 Anindita Ghosh, Bing Zhou, Rishabh Dabral, Jian Wang, Vladislav Golyanik, Christian Theobalt, Philipp Slusallek, Chuan Guo

Subsequently, in the second stage, two generative masked transformers learn to map music signals to these dance tokens: the first producing high-level semantic tokens, and the second, conditioned on music and these semantic tokens, producing the low-level tokens.

Motion Synthesis

How much do language models memorize?

no code implementations30 May 2025 John X. Morris, Chawin Sitawarin, Chuan Guo, Narine Kokhlikyan, G. Edward Suh, Alexander M. Rush, Kamalika Chaudhuri, Saeed Mahloujifar

We propose a new method for estimating how much a model ``knows'' about a datapoint and use it to measure the capacity of modern language models.

Language Modeling Language Modelling +1

RoFL: Robust Fingerprinting of Language Models

1 code implementation19 May 2025 Yun-Yun Tsai, Chuan Guo, Junfeng Yang, Laurens van der Maaten

We present a new method that enable model developers to perform such identification via fingerprints: statistical patterns that are unique to the developer's model and robust to common alterations of that model.

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

1 code implementation22 Apr 2025 Ivan Evtimov, Arman Zharmagambetov, Aaron Grattafiori, Chuan Guo, Kamalika Chaudhuri

Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills.

Benchmarking

MotionDreamer: One-to-Many Motion Synthesis with Localized Generative Masked Transformer

no code implementations11 Apr 2025 Yilin Wang, Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Xinxin Zuo, Juwei Lu, Hai Jiang, Li Cheng

In this work, we present MotionDreamer, a localized masked modeling paradigm designed to learn internal motion patterns from a given motion with arbitrary topology and duration.

Motion Synthesis Quantization

SceneMI: Motion In-betweening for Modeling Human-Scene Interactions

no code implementations20 Mar 2025 Inwoo Hwang, Bing Zhou, Young Min Kim, Jian Wang, Chuan Guo

Modeling human-scene interactions (HSI) is essential for understanding and simulating everyday human behaviors.

Denoising motion in-betweening

A Survey on Human Interaction Motion Generation

1 code implementation17 Mar 2025 Kewei Sui, Anindita Ghosh, Inwoo Hwang, Jian Wang, Chuan Guo

Humans inhabit a world defined by interactions -- with other humans, objects, and environments.

Human Dynamics Motion Generation +1

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

1 code implementation12 Mar 2025 Arman Zharmagambetov, Chuan Guo, Ivan Evtimov, Maya Pavlova, Ruslan Salakhutdinov, Kamalika Chaudhuri

In this work, we propose one way to address that potential risk, by training AI agents to better satisfy the privacy principle of data minimization.

Detecting Benchmark Contamination Through Watermarking

no code implementations24 Feb 2025 Tom Sander, Pierre Fernandez, Saeed Mahloujifar, Alain Durmus, Chuan Guo

Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set.

ARC MMLU

AdvPrefix: An Objective for Nuanced LLM Jailbreaks

1 code implementation13 Dec 2024 Sicheng Zhu, Brandon Amos, Yuandong Tian, Chuan Guo, Ivan Evtimov

To address these limitations, we introduce AdvPrefix, a new prefix-forcing objective that enables more nuanced control over model behavior while being easy to optimize.

ControlMM: Controllable Masked Motion Generation

no code implementations14 Oct 2024 Ekkasit Pinyoanuntapong, Muhammad Usama Saleem, Korrawe Karunratanakul, Pu Wang, Hongfei Xue, Chen Chen, Chuan Guo, Junli Cao, Jian Ren, Sergey Tulyakov

To further enhance control precision, we introduce inference-time logit editing, which manipulates the predicted conditional motion distribution so that the generated motion, sampled from the adjusted distribution, closely adheres to the input control signals.

Motion Generation

InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling

1 code implementation13 Oct 2024 Muhammad Gohar Javed, Chuan Guo, Li Cheng, Xingyu Li

In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space.

Motion Synthesis

RegionGrasp: A Novel Task for Contact Region Controllable Hand Grasp Generation

no code implementations10 Oct 2024 Yilin Wang, Chuan Guo, Li Cheng, Hai Jiang

This motivates us to consider a novel task of \textit{Region Controllable Hand Grasp Generation (RegionGrasp)}, as follows: given as input a 3D object, together with its specific surface area selected as the intended contact region, to generate a diverse set of plausible hand grasps of the object, where the thumb finger tip touches the object surface on the contact region.

Grasp Generation Object

SecAlign: Defending Against Prompt Injection with Preference Optimization

1 code implementation7 Oct 2024 Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar, Kamalika Chaudhuri, David Wagner, Chuan Guo

We then perform preference optimization on this dataset to teach the LLM to prefer the secure output over the insecure one.

GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction

no code implementations5 Jul 2024 Yuxuan Mu, Xinxin Zuo, Chuan Guo, Yilin Wang, Juwei Lu, Xiaofeng Wu, Songcen Xu, Peng Dai, Youliang Yan, Li Cheng

We present GSD, a diffusion model approach based on Gaussian Splatting (GS) representation for 3D object reconstruction from a single view.

3D geometry 3D Object Reconstruction +2

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

1 code implementation21 Apr 2024 Anselm Paulus, Arman Zharmagambetov, Chuan Guo, Brandon Amos, Yuandong Tian

We also show that training on adversarial suffixes generated by AdvPrompter is a promising strategy for improving the robustness of LLMs to jailbreaking attacks.

MMLU Red Teaming

Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds

1 code implementation3 Apr 2024 Kamalika Chaudhuri, Chuan Guo, Laurens van der Maaten, Saeed Mahloujifar, Mark Tygert

The HCR bounds appear to be insufficient on their own to guarantee confidentiality of the inputs to inference with standard deep neural nets, "ResNet-18" and "Swin-T," pre-trained on the data set, "ImageNet-1000," which contains 1000 classes.

image-classification Image Classification

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning

1 code implementation21 Mar 2024 Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi, Adriana Romero-Soriano, Kamalika Chaudhuri, Mike Rabbat, Chuan Guo

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable.

Memorization Retrieval +1

Privacy Amplification for the Gaussian Mechanism via Bounded Support

no code implementations7 Mar 2024 Shengyuan Hu, Saeed Mahloujifar, Virginia Smith, Kamalika Chaudhuri, Chuan Guo

Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset.

Differentially Private Representation Learning via Image Captioning

1 code implementation4 Mar 2024 Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo

In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets.

Image Captioning Representation Learning

Déjà Vu Memorization in Vision-Language Models

no code implementations3 Feb 2024 Bargav Jayaraman, Chuan Guo, Kamalika Chaudhuri

Vision-Language Models (VLMs) have emerged as the state-of-the-art representation learning solution, with myriads of downstream applications such as image classification, retrieval and generation.

image-classification Image Classification +3

Generative Human Motion Stylization in Latent Space

no code implementations24 Jan 2024 Chuan Guo, Yuxuan Mu, Xinxin Zuo, Peng Dai, Youliang Yan, Juwei Lu, Li Cheng

Building upon this, we present a novel generative model that produces diverse stylization results of a single motion (latent) code.

MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation

1 code implementation20 Jan 2024 Nhat M. Hoang, Kehong Gong, Chuan Guo, Michael Bi Mi

Specifically, we separate the denoising objectives of a diffusion model into two stages: obtaining conditional rough motion approximations in the initial $T-T^*$ steps by learning the noisy annotated motions, followed by the unconditional refinement of these preliminary motions during the last $T^*$ steps using unannotated motions.

Denoising Motion Generation

MoMask: Generative Masked Modeling of 3D Human Motions

1 code implementation CVPR 2024 Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng

For the base-layer motion tokens, a Masked Transformer is designated to predict randomly masked motion tokens conditioned on text input at training stage.

Human motion prediction Motion Forecasting +3

Large-Scale Public Data Improves Differentially Private Image Generation Quality

no code implementations4 Aug 2023 Ruihan Wu, Chuan Guo, Kamalika Chaudhuri

In this work, we look at how to use generic large-scale public data to improve the quality of differentially private image generation in Generative Adversarial Networks (GANs), and provide an improved method that uses public data effectively.

Image Generation

ViP: A Differentially Private Foundation Model for Computer Vision

1 code implementation15 Jun 2023 Yaodong Yu, Maziar Sanjabi, Yi Ma, Kamalika Chaudhuri, Chuan Guo

In this work, we propose as a mitigation measure a recipe to train foundation vision models with differential privacy (DP) guarantee.

"Private Prediction Strikes Back!'' Private Kernelized Nearest Neighbors with Individual Renyi Filter

1 code implementation12 Jun 2023 Yuqing Zhu, Xuandong Zhao, Chuan Guo, Yu-Xiang Wang

Most existing approaches of differentially private (DP) machine learning focus on private training.

Information Flow Control in Machine Learning through Modular Model Architecture

no code implementations5 Jun 2023 Trishita Tiwari, Suchin Gururangan, Chuan Guo, Weizhe Hua, Sanjay Kariyappa, Udit Gupta, Wenjie Xiong, Kiwan Maeng, Hsien-Hsin S. Lee, G. Edward Suh

This lack of control for information flow from training data to model output is a major obstacle in training models on sensitive data when access control only allows individual users to access a subset of data.

Language Modeling Language Modelling

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

1 code implementation NeurIPS 2023 Casey Meehan, Florian Bordes, Pascal Vincent, Kamalika Chaudhuri, Chuan Guo

Self-supervised learning (SSL) algorithms can produce useful image representations by learning to associate different parts of natural images with one another.

Memorization Self-Supervised Learning

Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design

1 code implementation8 Nov 2022 Chuan Guo, Kamalika Chaudhuri, Pierre Stock, Mike Rabbat

In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model.

Federated Learning

Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano

no code implementations24 Oct 2022 Chuan Guo, Alexandre Sablayrolles, Maziar Sanjabi

Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy risks in machine learning.

Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning

1 code implementation19 Oct 2022 Ruihan Wu, Xiangyu Chen, Chuan Guo, Kilian Q. Weinberger

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy.

Federated Learning

Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information

no code implementations21 Sep 2022 Kiwan Maeng, Chuan Guo, Sanjay Kariyappa, Edward Suh

Split learning and inference propose to run training/inference of a large model that is split across client devices and the cloud.

Origins of Low-dimensional Adversarial Perturbations

no code implementations25 Mar 2022 Elvis Dohmatob, Chuan Guo, Morgane Goibert

Finally, we show that if a decision-region is compact, then it admits a universal adversarial perturbation with $L_2$ norm which is $\sqrt{d}$ times smaller than the typical $L_2$ norm of a data point.

Privacy-Aware Compression for Federated Data Analysis

1 code implementation15 Mar 2022 Kamalika Chaudhuri, Chuan Guo, Mike Rabbat

Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of distributed low-bandwidth user devices to estimate aggregate statistics.

Federated Learning

Does Label Differential Privacy Prevent Label Inference Attacks?

1 code implementation25 Feb 2022 Ruihan Wu, Jin Peng Zhou, Kilian Q. Weinberger, Chuan Guo

Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels.

Bounding Training Data Reconstruction in Private (Deep) Learning

1 code implementation28 Jan 2022 Chuan Guo, Brian Karrer, Kamalika Chaudhuri, Laurens van der Maaten

Differential privacy is widely accepted as the de facto method for preventing data leakage in ML, and conventional wisdom suggests that it offers strong protection against privacy attacks.

Deep Learning

Submix: Practical Private Prediction for Large-Scale Language Models

no code implementations4 Jan 2022 Antonio Ginart, Laurens van der Maaten, James Zou, Chuan Guo

Recent data-extraction attacks have exposed that language models can memorize some training samples verbatim.

Language Modeling Language Modelling

ReAct: Out-of-distribution Detection With Rectified Activations

1 code implementation NeurIPS 2021 Yiyou Sun, Chuan Guo, Yixuan Li

Out-of-distribution (OOD) detection has received much attention lately due to its practical importance in enhancing the safe deployment of neural networks.

Out-of-Distribution Detection

On the Importance of Difficulty Calibration in Membership Inference Attacks

1 code implementation ICLR 2022 Lauren Watson, Chuan Guo, Graham Cormode, Alex Sablayrolles

The vulnerability of machine learning models to membership inference attacks has received much attention in recent years.

Action2video: Generating Videos of Human 3D Actions

no code implementations12 Nov 2021 Chuan Guo, Xinxin Zuo, Sen Wang, Xinshuang Liu, Shihao Zou, Minglun Gong, Li Cheng

Action2motion stochastically generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos.

EventHPE: Event-based 3D Human Pose and Shape Estimation

1 code implementation ICCV 2021 Shihao Zou, Chuan Guo, Xinxin Zuo, Sen Wang, Pengyu Wang, Xiaoqin Hu, Shoushun Chen, Minglun Gong, Li Cheng

Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals.

3D human pose and shape estimation Optical Flow Estimation

Human Pose and Shape Estimation from Single Polarization Images

1 code implementation15 Aug 2021 Shihao Zou, Xinxin Zuo, Sen Wang, Yiming Qian, Chuan Guo, Li Cheng

This paper focuses on a new problem of estimating human pose and shape from single polarization images.

Surface Normal Estimation

Online Adaptation to Label Distribution Shift

no code implementations NeurIPS 2021 Ruihan Wu, Chuan Guo, Yi Su, Kilian Q. Weinberger

Machine learning models often encounter distribution shifts when deployed in the real world.

Byzantine-Robust and Privacy-Preserving Framework for FedML

no code implementations5 May 2021 Hanieh Hashemi, Yongqin Wang, Chuan Guo, Murali Annavaram

This learning setting presents, among others, two unique challenges: how to protect privacy of the clients' data during training, and how to ensure integrity of the trained model.

Federated Learning Privacy Preserving

Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems

1 code implementation NeurIPS 2021 Ruihan Wu, Chuan Guo, Awni Hannun, Laurens van der Maaten

Machine-learning systems such as self-driving cars or virtual assistants are composed of a large number of machine-learning models that recognize image content, transcribe speech, analyze natural language, infer preferences, rank options, etc.

BIG-bench Machine Learning Object Detection +1

Measuring Data Leakage in Machine-Learning Models with Fisher Information

1 code implementation23 Feb 2021 Awni Hannun, Chuan Guo, Laurens van der Maaten

This information leaks either through the model itself or through predictions made by the model.

BIG-bench Machine Learning

Making Paper Reviewing Robust to Bid Manipulation Attacks

1 code implementation9 Feb 2021 Ruihan Wu, Chuan Guo, Felix Wu, Rahul Kidambi, Laurens van der Maaten, Kilian Q. Weinberger

We develop a novel approach for paper bidding and assignment that is much more robust against such attacks.

Action2Motion: Conditioned Generation of 3D Human Motions

1 code implementation30 Jul 2020 Chuan Guo, Xinxin Zuo, Sen Wang, Shihao Zou, Qingyao Sun, Annan Deng, Minglun Gong, Li Cheng

Action recognition is a relatively established task, where givenan input sequence of human motion, the goal is to predict its ac-tion category.

Action Generation

Polarization Human Shape and Pose Dataset

no code implementations30 Apr 2020 Shihao Zou, Xinxin Zuo, Yiming Qian, Sen Wang, Chuan Guo, Chi Xu, Minglun Gong, Li Cheng

Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing detailed surface normal of the objects of interest.

On Hiding Neural Networks Inside Neural Networks

no code implementations24 Feb 2020 Chuan Guo, Ruihan Wu, Kilian Q. Weinberger

Modern neural networks often contain significantly more parameters than the size of their training data.

BIG-bench Machine Learning

Secure multiparty computations in floating-point arithmetic

no code implementations9 Jan 2020 Chuan Guo, Awni Hannun, Brian Knott, Laurens van der Maaten, Mark Tygert, Ruiyu Zhu

Secure multiparty computations enable the distribution of so-called shares of sensitive data to multiple parties such that the multiple parties can effectively process the data while being unable to glean much information about the data (at least not without collusion among all parties to put back together all the shares).

All Mathematical Proofs +2

Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces

no code implementations NeurIPS 2019 Chuan Guo, Ali Mousavi, Xiang Wu, Daniel N. Holtmann-Rice, Satyen Kale, Sashank Reddi, Sanjiv Kumar

In extreme classification settings, embedding-based neural network models are currently not competitive with sparse linear and tree-based methods in terms of accuracy.

Attribute Classification +2

A New Defense Against Adversarial Images: Turning a Weakness into a Strength

1 code implementation NeurIPS 2019 Tao Yu, Shengyuan Hu, Chuan Guo, Wei-Lun Chao, Kilian Q. Weinberger

Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial images.

Adversarial Defense

Simple Black-box Adversarial Attacks

5 code implementations ICLR 2019 Chuan Guo, Jacob R. Gardner, Yurong You, Andrew Gordon Wilson, Kilian Q. Weinberger

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting.

Low Frequency Adversarial Perturbation

1 code implementation24 Sep 2018 Chuan Guo, Jared S. Frank, Kilian Q. Weinberger

In this paper we propose to restrict the search for adversarial images to a low frequency domain.

Denoising Speech Recognition

Countering Adversarial Images using Input Transformations

1 code implementation ICLR 2018 Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens van der Maaten

This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system.

Adversarial Defense General Classification +2

On Calibration of Modern Neural Networks

15 code implementations ICML 2017 Chuan Guo, Geoff Pleiss, Yu Sun, Kilian Q. Weinberger

Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications.

Document Classification General Classification

Supervised Word Mover's Distance

1 code implementation NeurIPS 2016 Gao Huang, Chuan Guo, Matt J. Kusner, Yu Sun, Fei Sha, Kilian Q. Weinberger

Accurately measuring the similarity between text documents lies at the core of many real world applications of machine learning.

Document Classification General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.