Cover Image

Provable Unrestricted Adversarial Training without Compromise with Generalizability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Lilin, Yang, Ning, Sun, Yanchao, Yu, Philip S.
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
by: Liu, Xiangyu, et al.
Published: (2023)

Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment
by: Xian, Guanmeng, et al.
Published: (2026)

Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
by: Xu, Tian, et al.
Published: (2024)

Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
by: Xian, Guanmeng, et al.
Published: (2026)

C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness
by: Kang, Yu, et al.
Published: (2024)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
by: Zhang, Lilin, et al.
Published: (2026)

Negative Metric Learning for Graphs
by: Zhao, Yiyang, et al.
Published: (2025)

Effective Universal Unrestricted Adversarial Attacks using a MOE Approach
by: Baia, A. E., et al.
Published: (2021)

Provable Training for Graph Contrastive Learning
by: Yu, Yue, et al.
Published: (2023)

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
by: Dai, Zeyu, et al.
Published: (2025)

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
by: Dai, Xuelong, et al.
Published: (2023)

Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
by: Liang, Hao, et al.
Published: (2025)

SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training
by: Zhang, Lu, et al.
Published: (2024)

Trustworthy Feature Importance Avoids Unrestricted Permutations
by: Borgonovo, Emanuele, et al.
Published: (2026)

Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
by: Chen, Peng, et al.
Published: (2025)

Non-Adversarial Imitation Learning Provably Free of Compounding Errors: The Role of Bellman Constraints
by: Xu, Tian, et al.
Published: (2026)

Merit-based Fair Combinatorial Semi-Bandit with Unrestricted Feedback Delays
by: Chen, Ziqun, et al.
Published: (2024)

Detecting Adversarial Data via Provable Adversarial Noise Amplification
by: Mumcu, Furkan, et al.
Published: (2026)

Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
by: Li, Binghui, et al.
Published: (2024)

DP-Dueling: Learning from Preference Feedback without Compromising User Privacy
by: Saha, Aadirupa, et al.
Published: (2024)

Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
by: Xin, Yuan, et al.
Published: (2023)

Democratic Training Against Universal Adversarial Perturbations
by: Sun, Bing, et al.
Published: (2025)

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
by: Liu, Zhihan, et al.
Published: (2024)

Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
by: Wang, Mengxuan, et al.
Published: (2026)

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
by: Labiad, Ismail, et al.
Published: (2025)

MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Search
by: Kim, Sungyoon, et al.
Published: (2025)

Ignoring Directionality Leads to Compromised Graph Neural Network Explanations
by: Sun, Changsheng, et al.
Published: (2025)

Test-Time Training Provably Improves Transformers as In-context Learners
by: Gozeten, Halil Alperen, et al.
Published: (2025)

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training
by: Bu, Dake, et al.
Published: (2025)

Provable Robustness Against a Union of $\ell_0$ Adversarial Attacks
by: Hammoudeh, Zayd, et al.
Published: (2023)

Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
by: Chen, Yilei, et al.
Published: (2024)

Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity
by: Kobayashi, Yuya, et al.
Published: (2025)

Provably Safe Model Updates
by: Elmecker-Plakolm, Leo, et al.
Published: (2025)

Regularized Gradient Clipping Provably Trains Wide and Deep Neural Networks
by: Tucat, Matteo, et al.
Published: (2024)

Adversarial Training of Reward Models
by: Bukharin, Alexander, et al.
Published: (2025)

Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy
by: Krüger, Fabian P., et al.
Published: (2024)

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
by: Zhang, Zhizhen, et al.
Published: (2025)

ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis
by: Zhang, Zhanqi, et al.
Published: (2026)

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
by: Liu, Chen, et al.
Published: (2021)

Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
by: Ye, Haotian, et al.
Published: (2022)