3 citations · 16 across the 42 of their papers we have counts for
4 papers · 1 filter
Pre-trained Trojan Attacks for Visual Recognition
Aishan Liu, Xinwei Zhang, Yisong Xiao +6
Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors with…
Adversarial Examples in the Physical World: A Survey
Jiakai Wang, Xianglong Liu, Jin Hu +6
Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples, raising broad security concerns about their applications. Besides the attacks in the digit…
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
Simin Li, Ruixiao Xu, Jingqiao Xiu +4
In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL m…
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
Wei Huang, Haotong Qin, Yangdong Liu +4
Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixtur…