b'Chaowei Xiao'

research

∙ 09/14/2023

Semantic Adversarial Attacks via Diffusion Models

Traditional adversarial attacks concentrate on manipulating clean exampl...

0 Chenan Wang, et al. ∙

research

∙ 09/01/2023

Reinforcement Learning with Human Feedback for Realistic Traffic Simulation

In light of the challenges and costs of real-world testing, autonomous v...

0 Yulong Cao, et al. ∙

research

∙ 08/28/2023

DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing

Diffusion models have been leveraged to perform adversarial purification...

0 Jiawei Zhang, et al. ∙

research

∙ 06/28/2023

On the Exploitability of Instruction Tuning

Instruction tuning is an effective technique to align large language mod...

0 Manli Shu, et al. ∙

research

∙ 06/27/2023

Differentially Private Video Activity Recognition

In recent years, differential privacy has seen significant advancements ...

0 Zelun Luo, et al. ∙

research

∙ 06/01/2023

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

Perception is crucial in the realm of autonomous driving systems, where ...

0 Jiachen Sun, et al. ∙

research

∙ 05/25/2023

Voyager: An Open-Ended Embodied Agent with Large Language Models

We introduce Voyager, the first LLM-powered embodied lifelong learning a...

16 Guanzhi Wang, et al. ∙

research

∙ 05/24/2023

Adversarial Demonstration Attacks on Large Language Models

With the emergence of more powerful large language models (LLMs), such a...

0 Jiongxiao Wang, et al. ∙

research

∙ 05/24/2023

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

Language models are often at risk of diverse backdoor attacks, especiall...

0 Qin Liu, et al. ∙

research

∙ 05/24/2023

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models

Instruction-tuned models are trained on crowdsourcing datasets with task...

0 Jiashu Xu, et al. ∙

research

∙ 05/03/2023

Defending against Insertion-based Textual Backdoor Attacks via Attribution

Textual backdoor attack, as a novel attack model, has been shown to be e...

0 Jiazhao Li, et al. ∙

research

∙ 04/27/2023

ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger

Textual backdoor attacks pose a practical threat to existing systems, as...

0 Jiazhao Li, et al. ∙

research

∙ 04/13/2023

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study

Large decoder-only language models (LMs) can be largely improved in term...

16 Boxin Wang, et al. ∙

research

∙ 03/30/2023

Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Sampling

In this work, we present a data poisoning attack that confounds machine ...

0 Ethan Wisdom, et al. ∙

research

∙ 03/27/2023

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Deep neural networks are proven to be vulnerable to backdoor attacks. De...

0 Xiaogeng Liu, et al. ∙

research

∙ 03/04/2023

Prismer: A Vision-Language Model with An Ensemble of Experts

Recent vision-language models have shown impressive multi-modal generati...

12 Shikun Liu, et al. ∙

research

∙ 03/02/2023

Defending against Adversarial Audio via Diffusion Model

Deep learning models have been widely used in commercial acoustic system...

0 Shutong Wu, et al. ∙

research

∙ 02/23/2023

VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion

Humans can easily imagine the complete 3D geometry of occluded objects a...

11 Yiming Li, et al. ∙

research

∙ 02/13/2023

PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees

Personalized Federated Learning (pFL) has emerged as a promising solutio...

1 Chulin Xie, et al. ∙

research

∙ 02/09/2023

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning

Augmenting pretrained language models (LMs) with a vision encoder (e.g.,...

0 Zhuolin Yang, et al. ∙

research

∙ 11/01/2022

DensePure: Understanding Diffusion Models towards Adversarial Robustness

Diffusion models have been recently employed to improve certified robust...

7 Chaowei Xiao, et al. ∙

research

∙ 09/19/2022

AdvDO: Realistic Adversarial Attacks for Trajectory Prediction

Trajectory prediction is essential for autonomous vehicles (AVs) to plan...

27 Yulong Cao, et al. ∙

research

∙ 09/15/2022

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

Pre-trained vision-language models (e.g., CLIP) have shown promising zer...

29 Manli Shu, et al. ∙

research

∙ 08/23/2022

Retrieval-based Controllable Molecule Generation

Generating new molecules with specified chemical and biological properti...

21 Zichao Wang, et al. ∙

research

∙ 08/21/2022

PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition

3D Point cloud is becoming a critical data representation in many real-w...

5 Jiachen Sun, et al. ∙

research

∙ 07/29/2022

Robust Trajectory Prediction against Adversarial Attacks

Trajectory prediction using deep neural networks (DNNs) is an essential ...

12 Yulong Cao, et al. ∙

research

∙ 07/25/2022

SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination

Transfer learning through the use of pre-trained models has become a gro...

0 Zhuowen Yuan, et al. ∙

research

∙ 05/16/2022

Diffusion Models for Adversarial Purification

Adversarial purification refers to a class of defense methods that remov...

38 Weili Nie, et al. ∙

research

∙ 04/26/2022

Understanding The Robustness in Vision Transformers

Recent studies show that Vision Transformers(ViTs) exhibit strong robust...

13 Daquan Zhou, et al. ∙

research

∙ 04/24/2022

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Reasoning about visual relationships is central to how humans interpret ...

6 Xiaojian Ma, et al. ∙

research

∙ 02/08/2022

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

Pre-trained language models (LMs) are shown to easily generate toxic lan...

16 Boxin Wang, et al. ∙

research

∙ 10/26/2021

AugMax: Adversarial Composition of Random Augmentations for Robust Training

Data augmentation is a simple yet effective way to improve the robustnes...

27 Haotao Wang, et al. ∙

research

∙ 09/25/2021

Auditing AI models for Verified Deployment under Semantic Specifications

Auditing trained deep learning (DL) models prior to deployment is vital ...

0 Homanga Bharadhwaj, et al. ∙

research

∙ 07/05/2021

Long-Short Transformer: Efficient Transformers for Language and Vision

Transformers have achieved success in both language and vision domains. ...

12 Chen Zhu, et al. ∙

research

∙ 06/17/2021

Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks

In Autonomous Driving (AD) systems, perception is both security and safe...

0 Yulong Cao, et al. ∙

research

∙ 06/09/2021

Practical Machine Learning Safety: A Survey and Primer

The open-world deployment of Machine Learning (ML) algorithms in safety-...

0 Sina Mohseni, et al. ∙

research

∙ 03/19/2020

Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations

Deep Reinforcement Learning (DRL) is vulnerable to small adversarial per...

0 Huan Zhang, et al. ∙

research

∙ 07/21/2019

Characterizing Attacks on Deep Reinforcement Learning

Deep reinforcement learning (DRL) has achieved great success in various ...

4 Chaowei Xiao, et al. ∙

research

∙ 07/16/2019

Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving

In Autonomous Vehicles (AVs), one fundamental pillar is perception, whic...

11 Yulong Cao, et al. ∙

research

∙ 07/11/2019

Adversarial Objects Against LiDAR-Based Autonomous Driving Systems

Deep neural networks (DNNs) are found to be vulnerable against adversari...

10 Yulong Cao, et al. ∙

research

∙ 06/19/2019

SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing

Deep neural networks (DNNs) have achieved great success in various appli...

7 Haonan Qiu, et al. ∙

research

∙ 06/14/2019

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

Training neural networks with verifiable robustness guarantees is challe...

0 Huan Zhang, et al. ∙

research

∙ 12/26/2018

Protecting Sensitive Attributes via Generative Adversarial Networks

Recent advances in computing have allowed for the possibility to collect...

0 Aria Rezaei, et al. ∙

research

∙ 10/30/2018

Data Poisoning Attack against Unsupervised Node Embedding Methods

Unsupervised node embedding methods (e.g., DeepWalk, LINE, and node2vec)...

4 Mingjie Sun, et al. ∙

research

∙ 10/11/2018

Realistic Adversarial Examples in 3D Meshes

Highly expressive models such as deep neural networks (DNNs) have been w...

0 Dawei Yang, et al. ∙

research

∙ 10/11/2018

Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation

Deep Neural Networks (DNNs) have been widely applied in various recognit...

0 Chaowei Xiao, et al. ∙

research

∙ 01/08/2018

Spatially transformed adversarial examples

Recent studies show that widely used deep neural networks (DNNs) are vul...

0 Chaowei Xiao, et al. ∙

research

∙ 01/08/2018

Generating adversarial examples with adversarial networks

Deep neural networks (DNNs) have been found to be vulnerable to adversar...

0 Chaowei Xiao, et al. ∙

Chaowei Xiao

Featured Co-authors