Image de couverture de livre

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Yunrui, Su, Hang, Zhu, Jun
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function
par: Yu, Yunrui, et autres
Publié: (2025)

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss
par: Yu, Yunrui, et autres
Publié: (2025)

Ignition Phase : Standard Training for Fast Adversarial Robustness
par: Yu-Hang, Wang, et autres
Publié: (2025)

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
par: Cao, Yuan-dong, et autres
Publié: (2026)

Deriving the Scaled-Dot-Function via Maximum Likelihood Estimation and Maximum Entropy Approach
par: Ma, Jiyong
Publié: (2025)

Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
par: Yamabe, Shojiro, et autres
Publié: (2024)

Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness
par: Khachaturov, David, et autres
Publié: (2024)

Why Do Neural Networks Forget: A Study of Collapse in Continual Learning
par: Zhu, Yunqin, et autres
Publié: (2026)

Maintaining Adversarial Robustness in Continuous Learning
par: Ru, Xiaolei, et autres
Publié: (2024)

Adversarial Robustness Overestimation and Instability in TRADES
par: Li, Jonathan Weiping, et autres
Publié: (2024)

Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
par: Decker, Thomas, et autres
Publié: (2025)

Adversarial Preference Learning for Robust LLM Alignment
par: Wang, Yuanfu, et autres
Publié: (2025)

Adversarially Robust Decision Transformer
par: Tang, Xiaohang, et autres
Publié: (2024)

Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
par: Zhou, MingWei, et autres
Publié: (2025)

Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness
par: Wang, Dingrong, et autres
Publié: (2024)

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
par: Jin, Ruinan, et autres
Publié: (2026)

How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness
par: Rossolini, Giulio
Publié: (2026)

Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness
par: Pal, Ambar, et autres
Publié: (2023)

Exploratory Diffusion Model for Unsupervised Reinforcement Learning
par: Ying, Chengyang, et autres
Publié: (2025)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
par: Ying, Chengyang, et autres
Publié: (2022)

Adversarial Diffusion for Robust Reinforcement Learning
par: Foffano, Daniele, et autres
Publié: (2025)

Algorithms for Adversarially Robust Deep Learning
par: Robey, Alexander
Publié: (2025)

Robust Decision Aggregation with Adversarial Experts
par: Guo, Yongkang, et autres
Publié: (2024)

Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
par: Wang, Longwei, et autres
Publié: (2025)

Total Variation Rates for Riemannian Flow Matching
par: Guan, Yunrui, et autres
Publié: (2026)

The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
par: Bell, Samuel J., et autres
Publié: (2024)

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
par: Li, Zaitang, et autres
Publié: (2023)

Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems
par: He, Jun, et autres
Publié: (2026)

Subgroups Matter for Robust Bias Mitigation
par: Alloula, Anissa, et autres
Publié: (2025)

Does Order Matter : Connecting The Law of Robustness to Robust Generalization
par: Mandal, Himadri, et autres
Publié: (2026)

CEAR: Certified Ensemble Adversarial Robustness in DNNs
par: Sadig, Daniel, et autres
Publié: (2026)

ROKA: Robust Knowledge Unlearning against Adversaries
par: Shin, Jinmyeong, et autres
Publié: (2026)

Adversarial Robustness of VAEs across Intersectional Subgroups
par: Ramanaik, Chethan Krishnamurthy, et autres
Publié: (2024)

Towards Adversarially Robust Deep Metric Learning
par: Ke, Xiaopeng
Publié: (2025)

Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness
par: Chen, Erh-Chung, et autres
Publié: (2024)

Explanation-Guided Adversarial Training for Robust and Interpretable Models
par: Chen, Chao, et autres
Publié: (2026)

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
par: Chen, Weixin, et autres
Publié: (2025)

Exploring Adversarial Robustness of Deep State Space Models
par: Qi, Biqing, et autres
Publié: (2024)

How Do Diffusion Models Improve Adversarial Robustness?
par: Yuezhang, Liu, et autres
Publié: (2025)

Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitization
par: Sun, Zexu, et autres
Publié: (2023)