Cover Image

Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Bongsoo, Lai, Rongjie, Li, Yao
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NPAT Null-Space Projected Adversarial Training Towards Zero Deterioration
by: Hu, Hanyi, et al.
Published: (2024)

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
by: Gao, Junqi, et al.
Published: (2024)

Differential Privacy Mechanisms in Neural Tangent Kernel Regression
by: Gu, Jiuxiang, et al.
Published: (2024)

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
by: Kirci, Onur Alp, et al.
Published: (2025)

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
by: Duan, Kaiwen, et al.
Published: (2025)

DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective
by: Shao, Shuo, et al.
Published: (2025)

Information Theoretic Adversarial Training of Large Language Models
by: Zhang, Yiwei, et al.
Published: (2026)

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
by: Wang, Yisen, et al.
Published: (2025)

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
by: Zhang, Yuxiang, et al.
Published: (2024)

Defending Against Unforeseen Failure Modes with Latent Adversarial Training
by: Casper, Stephen, et al.
Published: (2024)

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
by: Beerens, Lucas, et al.
Published: (2025)

Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
by: Luo, Xinjian, et al.
Published: (2024)

Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
by: Li, Jianwei, et al.
Published: (2026)

Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective
by: Li, Nan, et al.
Published: (2024)

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
by: Wu, Yuanwei, et al.
Published: (2023)

Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
by: Chen, Depeng, et al.
Published: (2024)

MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks
by: Zhang, Jiaming, et al.
Published: (2023)

A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
by: Dai, Jiazhu, et al.
Published: (2025)

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
by: Li, Ding, et al.
Published: (2024)

Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks
by: Dong, Wenhan, et al.
Published: (2024)

Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation
by: Shang, Yingjia, et al.
Published: (2025)

Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
by: Zeng, Qirun, et al.
Published: (2025)

Investigating the Impact of Quantization on Adversarial Robustness
by: Li, Qun, et al.
Published: (2024)

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
by: Liu, Zhenyu, et al.
Published: (2024)

Extracting Memorized Training Data via Decomposition
by: Su, Ellen, et al.
Published: (2024)

An Adversarial Perspective on Machine Unlearning for AI Safety
by: Łucki, Jakub, et al.
Published: (2024)

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications
by: Zhang, Lu, et al.
Published: (2025)

Self-interpreting Adversarial Images
by: Zhang, Tingwei, et al.
Published: (2024)

Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness
by: Khachaturov, David, et al.
Published: (2024)

Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models
by: Poudel, Bibek, et al.
Published: (2021)

Adversarial Machine Learning Threats to Spacecraft
by: Thummala, Rajiv, et al.
Published: (2024)

Topological Signatures of Adversaries in Multimodal Alignments
by: Vu, Minh, et al.
Published: (2025)

Adversarial Illusions in Multi-Modal Embeddings
by: Zhang, Tingwei, et al.
Published: (2023)

Are Robust LLM Fingerprints Adversarially Robust?
by: Nasery, Anshul, et al.
Published: (2025)

AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines
by: Li, Tingxi, et al.
Published: (2026)

Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
by: Németh, Gergely Dániel, et al.
Published: (2023)

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
by: Fakorede, Olukorede, et al.
Published: (2024)

On the Duality Between Sharpness-Aware Minimization and Adversarial Training
by: Zhang, Yihao, et al.
Published: (2024)

AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
by: Li, Fengpeng, et al.
Published: (2026)