146 citations · 1.1k across the 129 of their papers we have counts for
12 papers · 1 filter
Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models
Jing-Xiao Liao, Tianwei Zhang, Yu-Hao Jiang +3
The pursuit of autonomously self-improving models has attracted growing interest in the era of large-scale foundation models. Drawing inspiration from the concept of "enlightenment…
Communication-Efficient Verifiable Attention for LLM Inference
Ziqun Chen, Ming Wu, Michael Heinrich +4
Computation integrity of remote large language model (LLM) serving can be questionable. For conventional deep neural networks (DNNs), the existing TEE-shielded DNN partitioning (TS…
Rethinking Adversarial Training with Neural Tangent Kernel
Guanlin Li, Han Qiu, Shangwei Guo +2
Adversarial training (AT) is an important and attractive topic in deep learning security, exhibiting mysteries and odd properties. Recent studies of neural network training dynamic…
Alleviating the Effect of Data Imbalance on Adversarial Training
Guanlin Li, Guowen Xu, Tianwei Zhang
In this paper, we study adversarial training on datasets that obey the long-tailed distribution, which is practical but rarely explored in previous works. Compared with conventiona…
Omnipotent Adversarial Training in the Wild
Guanlin Li, Kangjie Chen, Yuan Xu +2
Adversarial training is an important topic in robust deep learning, but the community lacks attention to its practical usage. In this paper, we aim to resolve a real-world challeng…
Alleviating Robust Overfitting of Adversarial Training With Consistency Regularization
Shudong Zhang, Haichang Gao, Tianwei Zhang +2
Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust overf…
ShiftNAS: Towards Automatic Generation of Advanced Mulitplication-Less Neural Networks
Xiaoxuan Lou, Guowen Xu, Kangjie Chen +3
Multiplication-less neural networks significantly reduce the time and energy cost on the hardware platform, as the compute-intensive multiplications are replaced with lightweight b…
A General Framework for Defending Against Backdoor Attacks via Influence Graph
Xiaofei Sun, Jiwei Li, Xiaoya Li +5
In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attack…
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation Techniques
Han Qiu, Yi Zeng, Tianwei Zhang +2
It is extensively studied that Deep Neural Networks (DNNs) are vulnerable to Adversarial Examples (AEs). With more and more advanced adversarial attack methods have been developed,…
Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?
Kaidi Jin, Tianwei Zhang, Chao Shen +4
Deep Neural Networks are well known to be vulnerable to adversarial attacks and backdoor attacks, where minor modifications on the input are able to mislead the models to give wron…
Stealing Deep Reinforcement Learning Models for Fun and Profit
Kangjie Chen, Shangwei Guo, Tianwei Zhang +2
This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only…
Byzantine-resilient Decentralized Stochastic Gradient Descent
Shangwei Guo, Tianwei Zhang, Han Yu +4
Decentralized learning has gained great popularity to improve learning efficiency and preserve data privacy. Each computing node makes equal contribution to collaboratively learn a…