Cover Image

Principal Eigenvalue Regularization for Improved Worst-Class Certified Robustness of Smoothed Classifiers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Gaojie, Huang, Tianjin, Mu, Ronghui, Huang, Xiaowei
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing Robust Fairness via Confusional Spectral Regularization
by: Jin, Gaojie, et al.
Published: (2025)

Reconcile Certified Robustness and Accuracy for DNN-based Smoothed Majority Vote Classifier
by: Jin, Gaojie, et al.
Published: (2025)

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
by: Li, Xinyu, et al.
Published: (2025)

CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
by: Wang, Zixia, et al.
Published: (2025)

OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
by: Li, Xinyu, et al.
Published: (2026)

Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments
by: Jin, Gaojie, et al.
Published: (2024)

Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
by: Fang, Kun, et al.
Published: (2022)

Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
by: Jin, Gaojie, et al.
Published: (2026)

Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds
by: Yi, Xinping, et al.
Published: (2026)

S2O: Enhancing Adversarial Training with Second-Order Statistics of Weights
by: Jin, Gaojie, et al.
Published: (2026)

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
by: Huang, Tianjin, et al.
Published: (2025)

ThermoRL:Structure-Aware Reinforcement Learning for Protein Mutation Design to Enhance Thermostability
by: Wang, Xiangwen, et al.
Published: (2025)

Laplace-Bridged Randomized Smoothing for Fast Certified Robustness
by: Lin, Miao, et al.
Published: (2026)

Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
by: Fazlyab, Mahyar, et al.
Published: (2023)

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
by: Huang, Zhuoqun, et al.
Published: (2025)

Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
by: Park, Subeen, et al.
Published: (2025)

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
by: Chen, Cheng, et al.
Published: (2021)

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
by: Wu, Jiapeng, et al.
Published: (2023)

A Recipe for Improved Certifiable Robustness
by: Hu, Kai, et al.
Published: (2023)

Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing
by: Delattre, Blaise, et al.
Published: (2026)

RS-Reg: Probabilistic and Robust Certified Regression Through Randomized Smoothing
by: Rekavandi, Aref Miri, et al.
Published: (2024)

Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions
by: Wang, Fan, et al.
Published: (2024)

SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing
by: Zhong, Meiyu, et al.
Published: (2024)

Certified Adversarial Robustness via Partition-based Randomized Smoothing
by: Goli, Hossein, et al.
Published: (2024)

Feature-Space Smoothing: Certified Robustness of Deep Representations
by: Xia, Song, et al.
Published: (2026)

The Eigenvalues Entropy as a Classifier Evaluation Measure
by: Dembélé, Doulaye
Published: (2025)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
by: Lyu, Saiyue, et al.
Published: (2024)

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
by: Gao, Weizhi, et al.
Published: (2024)

Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization
by: Luo, Haocheng, et al.
Published: (2025)

Your Diffusion Model is Secretly a Certifiably Robust Classifier
by: Chen, Huanran, et al.
Published: (2024)

Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
by: Bai, Yatong, et al.
Published: (2023)

DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation
by: Yan, Yang, et al.
Published: (2026)

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
by: Liu, Xiangyu, et al.
Published: (2024)

Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness
by: Deng, Jieren, et al.
Published: (2024)

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
by: Xia, Song, et al.
Published: (2024)

Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Network
by: Wu, Dengyu, et al.
Published: (2024)

GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees
by: Shah, Arya, et al.
Published: (2026)

Enhanced Estimation Techniques for Certified Radii in Randomized Smoothing
by: Liang, Zixuan
Published: (2025)

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
by: Hu, Hanjiang, et al.
Published: (2023)

Towards the Worst-case Robustness of Large Language Models
by: Chen, Huanran, et al.
Published: (2025)