Initialization Matters for Adversarial Transfer Learning

v1v2 (latest)

Initialization Matters for Adversarial Transfer Learning

Computer Vision and Pattern Recognition (CVPR), 2023

10 December 2023

Jindong Gu

Nicholas Carlini

ArXiv (abs)PDF HTML Github (7★)

Papers citing "Initialization Matters for Adversarial Transfer Learning"

7 / 7 papers shown

Title
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling Jonas Ngnawé M. Heuillet Sabyasachi Sahoo Y. Pequignot Ola Ahmad Audrey Durand Frédéric Precioso Christian Gagné AAML 112 0 0 27 Sep 2025
A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy M. Heuillet Rishika Bhagwatkar Jonas Ngnawé Y. Pequignot Alexandre Larouche Christian Gagné Irina Rish Ola Ahmad Audrey Durand OOD AAML VLM 120 1 0 12 Aug 2025
Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies Chenruo Liu Kenan Tang Yao Qin Qi Lei 214 1 0 28 May 2025
On the Robustness Tradeoff in Fine-Tuning Kunyang Li Jean-Charles Noirot Ferrand Ryan Sheatsley Blaine Hoak Yohan Beugin Eric Pauley Patrick McDaniel 215 0 0 19 Mar 2025
Conflict-Aware Adversarial Training Zhiyu Xue Haohan Wang Yao Qin Ramtin Pedarsani AAML 281 0 0 21 Oct 2024
Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels Maria Marrium Arif Mahmood Mohammed Bennamoun NoLa AAML 213 0 0 05 Oct 2024
As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks? Anjun Hu Jindong Gu Francesco Pinto Konstantinos Kamnitsas Juil Sock AAML SILM 174 8 0 19 Mar 2024