455 citations · 971 across the 43 of their papers we have counts for
45 papers · 1 filter
HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression
Jiaqi Gu, Ben Keller, Jean Kossaifi +3
Transformers have attained superior performance in natural language processing and computer vision. Their self-attention and feedforward layers are overparameterized, limiting infe…
DensePure: Understanding Diffusion Models towards Adversarial Robustness
Chaowei Xiao, Zhongzhu Chen, Kun Jin +6
Diffusion models have been recently employed to improve certified robustness through the process of denoising. However, the theoretical understanding of why diffusion models are ab…
An Adversarial Active Sampling-based Data Augmentation Framework for Manufacturable Chip Design
Mingjie Liu, Haoyu Yang, Zongyi Li +7
Lithography modeling is a crucial problem in chip design to ensure a chip design mask is manufacturable. It requires rigorous simulations of optical and chemical models that are co…
AdvDO: Realistic Adversarial Attacks for Trajectory Prediction
Yulong Cao, Chaowei Xiao, Anima Anandkumar +2
Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few s…
Diffusion Models for Adversarial Purification
Weili Nie, Brandon Guo, Yujia Huang +3
Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model. These methods do not make assumptions on the form of a…
Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds
Yujia Huang, Huan Zhang, Yuanyuan Shi +2
Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by…