Safety and Performance, Why Not Both? Bi-Objective Optimized Model
Compression against Heterogeneous Attacks Toward AI Software Deployment

Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment

2 January 2024

Leye Wang

Papers citing "Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment"

8 / 8 papers shown

Title
Optimizing Deep Neural Networks using Safety-Guided Self Compression Mohammad Zbeeb Mariam Salman Mohammad Bazzi Ammar Mohanna 33 0 0 01 May 2025
Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability Vishnu Kabir Chhabra Mohammad Mahdi Khalili AI4CE 33 0 0 05 Apr 2025
MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts Jie Zhu Y. Chen Mingyu Ding Ping Luo Leye Wang Jingdong Wang DiffM 42 4 0 30 Oct 2024
M^4I: Multi-modal Models Membership Inference Pingyi Hu Zihan Wang Ruoxi Sun Hu Wang Minhui Xue 39 26 0 15 Sep 2022
Membership Inference Attacks Against Self-supervised Speech Models Wei-Cheng Tseng Wei-Tsung Kao Hung-yi Lee 38 14 0 09 Nov 2021
Systematic Evaluation of Privacy Risks of Machine Learning Models Liwei Song Prateek Mittal MIACV 196 359 0 24 Mar 2020
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 299 6,984 0 20 Apr 2018
U-Net: Convolutional Networks for Biomedical Image Segmentation Olaf Ronneberger Philipp Fischer Thomas Brox SSeg 3DV 375 75,972 0 18 May 2015