ICML 2024 "adversarial training" Papers

24 papers found

Adversarially Robust Deep Multi-View Clustering: A Novel Attack and Defense Framework

Haonan Huang, Guoxu Zhou, Yanghang Zheng et al.

ICML 2024poster

Adversarially Robust Hypothesis Transfer Learning

Yunjuan Wang, Raman Arora

ICML 2024poster

Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies

Brian Bartoldson, James Diffenderfer, Konstantinos Parasyris et al.

ICML 2024poster

A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks

Boqi Li, Weiwei Liu

ICML 2024spotlight

Benign Overfitting in Adversarial Training of Neural Networks

Yunjuan Wang, Kaibo Zhang, Raman Arora

ICML 2024poster

Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval

Qiwei Tian, Chenhao Lin, Zhengyu Zhao et al.

ICML 2024poster

Delving into the Convergence of Generalized Smooth Minimax Optimization

Wenhan Xian, Ziyi Chen, Heng Huang

ICML 2024poster

Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes

Daniil Vankov, Angelia Nedich, Lalitha Sankar

ICML 2024poster

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Mantas Mazeika, Long Phan, Xuwang Yin et al.

ICML 2024poster

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Jiacheng Zhang, Feng Liu, Dawei Zhou et al.

ICML 2024poster

Improving Adversarial Energy-Based Model via Diffusion Process

Cong Geng, Tian Han, Peng-Tao Jiang et al.

ICML 2024poster

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency

Runqi Lin, Chaojian Yu, Bo Han et al.

ICML 2024poster

Learning Decision Trees and Forests with Algorithmic Recourse

Kentaro Kanamori, Takuya Takagi, Ken Kobayashi et al.

ICML 2024spotlight

Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inference

Md Musfiqur Rahman, Murat Kocaoglu

ICML 2024poster

On the Duality Between Sharpness-Aware Minimization and Adversarial Training

Yihao Zhang, Hangzhou He, Jingyu Zhu et al.

ICML 2024poster

Position: What makes an image realistic?

Lucas Theis

ICML 2024spotlight

Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders

Yi Yu, Yufei Wang, Song Xia et al.

ICML 2024poster

Refining Minimax Regret for Unsupervised Environment Design

Michael Beukman, Samuel Coward, Michael Matthews et al.

ICML 2024poster

Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration

Xiaole Tang, Hu Xin, Xiang Gu et al.

ICML 2024poster

Robust Classification via a Single Diffusion Model

Huanran Chen, Yinpeng Dong, Zhengyi Wang et al.

ICML 2024poster

RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples

Hossein Mirzaei, Mohammad Jafari Varnousfaderani, Hamid Reza Dehbashi et al.

ICML 2024poster

The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks

Ziquan Liu, Yufei Cui, Yan Yan et al.

ICML 2024poster

Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations

Xuyang Zhong, Yixiao HUANG, Chen Liu

ICML 2024poster

Uniformly Stable Algorithms for Adversarial Training and Beyond

Jiancong Xiao, Jiawei Zhang, Zhi-Quan Luo et al.

ICML 2024poster