36 citations · 67 across the 9 of their papers we have counts for
9 papers
Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density
Shuangqi Li, Chen Liu, Tong Zhang +3
We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with either enhanced fidelity or increased diversity. Our approa…
Behavior Prior Representation learning for Offline Reinforcement Learning
Hongyu Zang, Xin Li, Jie Yu +4
Offline reinforcement learning (RL) struggles in environments with rich and noisy inputs, where the agent only has access to a fixed dataset without environment interactions. Past…
Fast Adversarial Training with Adaptive Step Size
Zhichao Huang, Yanbo Fan, Chen Liu +5
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it har…
Robust Binary Models by Pruning Randomly-initialized Networks
Chen Liu, Ziqi Zhao, Sabine Süsstrunk +1
Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet com…
On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
Chen Liu, Zhichao Huang, Mathieu Salzmann +2
Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this w…
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them
Chen Liu, Mathieu Salzmann, Tao Lin +2
We analyze the influence of adversarial training on the loss landscape of machine learning models. To this end, we first provide analytical studies of the properties of adversarial…
Training Provably Robust Models by Polyhedral Envelope Regularization
Chen Liu, Mathieu Salzmann, Sabine Süsstrunk
Training certifiable neural networks enables one to obtain models with robustness guarantees against adversarial attacks. In this work, we introduce a framework to bound the advers…
On Certifying Non-uniform Bound against Adversarial Attacks
Chen Liu, Ryota Tomioka, Volkan Cevher
This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In con…
Finding Mixed Nash Equilibria of Generative Adversarial Networks
Ya-Ping Hsieh, Chen Liu, Volkan Cevher
We reconsider the training objective of Generative Adversarial Networks (GANs) from the mixed Nash Equilibria (NE) perspective. Inspired by the classical prox methods, we develop a…