1.8k citations · 3.4k across the 56 of their papers we have counts for
56 papers
Smoothed Online Convex Optimization Based on Discounted-Normal-Predictor
Lijun Zhang, Wei Jiang, Jinfeng Yi +1
In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor (Kapralov and Panigrahy, 2010) for smoothed online convex optimization (SOCO), in w…
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
Yimeng Zhang, Yuguang Yao, Jinghan Jia +4
The lack of adversarial robustness has been recognized as an important issue for state-of-the-art machine learning (ML) models, e.g., deep neural networks (DNNs). Thereby, robustif…
Can Adversarial Training Be Manipulated By Non-Robust Features?
Lue Tao, Lei Feng, Hongxin Wei +3
Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability…
Federated Two-stage Learning with Sign-based Voting
Zichen Ma, Zihan Lu, Yu Lu +3
Federated learning is a distributed machine learning mechanism where local devices collaboratively train a shared global model under the orchestration of a central server, while ke…
On the Convergence and Robustness of Adversarial Training
Yisen Wang, Xingjun Ma, James Bailey +3
Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep learning. Across existing defense techniques…
How and When Adversarial Robustness Transfers in Knowledge Distillation?
Rulin Shao, Jinfeng Yi, Pin-Yu Chen +1
Knowledge distillation (KD) has been widely used in teacher-student training, with applications to model compression in resource-constrained deep learning. Current works mainly foc…
Adversarial Attack across Datasets
Yunxiao Qin, Yuanhao Xiong, Jinfeng Yi +2
Existing transfer attack methods commonly assume that the attacker knows the training set (e.g., the label set, the input size) of the black-box victim models, which is usually unr…
Trustworthy AI: From Principles to Practices
Bo Li, Peng Qi, Bo Liu +5
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to…
Training Meta-Surrogate Model for Transferable Adversarial Attack
Yunxiao Qin, Yuanhao Xiong, Jinfeng Yi +1
We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversari…
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Xinwei Zhang, Xiangyi Chen, Mingyi Hong +2
Providing privacy protection has been one of the primary motivations of Federated Learning (FL). Recently, there has been a line of work on incorporating the formal privacy notion…
Towards Heterogeneous Clients with Elastic Federated Learning
Zichen Ma, Yu Lu, Zihan Lu +3
Federated learning involves training machine learning models over devices or data silos, such as edge processors or data warehouses, while keeping the data local. Training in heter…
Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation
Sanshi Yu, Zhuoxuan Jiang, Dong-Dong Chen +4
Recently, a new form of online shopping becomes more and more popular, which combines live streaming with E-Commerce activity. The streamers introduce products and interact with th…
Universal Online Convex Optimization Meets Second-order Bounds
Lijun Zhang, Yibo Wang, Guanghui Wang +2
Recently, several universal methods have been proposed for online convex optimization, and attain minimax rates for multiple types of convex functions simultaneously. However, they…
Fast Certified Robust Training with Short Warmup
Zhouxing Shi, Yihan Wang, Huan Zhang +2
Recently, bound propagation based certified robust training methods have been proposed for training neural networks with certifiable robustness guarantees. Despite that state-of-th…
On the Adversarial Robustness of Vision Transformers
Rulin Shao, Zhouxing Shi, Jinfeng Yi +2
Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a…
Robust Text CAPTCHAs Using Adversarial Examples
Rulin Shao, Zhouxing Shi, Jinfeng Yi +2
CAPTCHA (Completely Automated Public Truing test to tell Computers and Humans Apart) is a widely used technology to distinguish real users and automated users such as bots. However…
On the Limitations of Denoising Strategies as Adversarial Defenses
Zhonghan Niu, Zhaoxi Chen, Linyi Li +3
As adversarial attacks against machine learning models have raised increasing concerns, many denoising-based defense approaches have been proposed. In this paper, we summarize and…
With False Friends Like These, Who Can Notice Mistakes?
Lue Tao, Lei Feng, Jinfeng Yi +1
Adversarial examples crafted by an explicit adversary have attracted significant attention in machine learning. However, the security risk posed by a potential false friend has bee…
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
Tianxin Wei, Fuli Feng, Jiawei Chen +3
The general aim of the recommender system is to provide personalized suggestions to users, which is opposed to suggesting popular items. However, the normal training paradigm, i.e.…
Provably Robust Metric Learning
Lu Wang, Xuanqing Liu, Jinfeng Yi +2
Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less…
Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data
Lu Wang, Huan Zhang, Jinfeng Yi +2
Adversarial black-box attacks aim to craft adversarial perturbations by querying input-output pairs of machine learning models. They are widely used to evaluate the robustness of p…
Symmetric Cross Entropy for Robust Learning with Noisy Labels
Yisen Wang, Xingjun Ma, Zaiyi Chen +3
Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning wi…
Characterizing Attacks on Deep Reinforcement Learning
Xinlei Pan, Chaowei Xiao, Warren He +8
Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations.…
Defending Against Adversarial Attacks Using Random Forests
Yifan Ding, Liqiang Wang, Huan Zhang +3
As deep neural networks (DNNs) have become increasingly important and popular, the robustness of DNNs is the key to the safety of both the Internet and the physical world. Unfortun…