Safety and Performance, Why not Both? Bi-Objective Optimized Model
Compression toward AI Software Deployment

v1v2 (latest)

Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment

11 August 2022

Leye Wang

ArXiv (abs)PDF HTML

Papers citing "Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment"

7 / 7 papers shown

Title
Auditing Data Provenance in Real-world Text-to-Image Diffusion Models for Privacy and Copyright Protection Jie Zhu Leye Wang 31 0 0 13 Jun 2025
A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability Jie Zhu Jirong Zha Ding Li Leye Wang 147 1 0 15 May 2025
Optimizing Deep Neural Networks using Safety-Guided Self Compression Mohammad Zbeeb Mariam Salman Mohammad Bazzi Ammar Mohanna 69 0 0 01 May 2025
MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts Jie Zhu Yukang Chen Mingyu Ding Ping Luo Leye Wang Jingdong Wang DiffM 69 5 0 30 Oct 2024
Efficient DNN-Powered Software with Fair Sparse Models Xuanqi Gao Weipeng Jiang Juan Zhai Shiqing Ma Xiaoyu Zhang Chao Shen 103 0 0 03 Jul 2024
A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability Jie Zhu Jirong Zha Ding Li Leye Wang 97 8 0 03 Apr 2024
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment Jie Zhu Leye Wang Xiao Han Anmin Liu Tao Xie AAML 117 6 0 02 Jan 2024