Copertina

Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Atienza, Nicolas, Labreuche, Christophe, Cohen, Johanne, Sebag, Michele
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Intermediate Layer Classifiers for OOD generalization
di: Uselis, Arnas, et al.
Pubblicazione: (2025)

Asymmetrical Latent Representation for Individual Treatment Effect Modeling
di: Lacombe, Armand, et al.
Pubblicazione: (2025)

A VAE Approach to Sample Multivariate Extremes
di: Lafon, Nicolas, et al.
Pubblicazione: (2023)

Hoeffding Concept Bottleneck Models with Applications to Overhead Images
di: Bénard, Clément, et al.
Pubblicazione: (2026)

PRIVET: Privacy Metric Based on Extreme Value Theory
di: Szatkownik, Antoine, et al.
Pubblicazione: (2025)

Your Classifier Can Be Secretly a Likelihood-Based OOD Detector
di: Burapacheep, Jirayu, et al.
Pubblicazione: (2024)

Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges
di: Poinsot, Audrey, et al.
Pubblicazione: (2024)

A Job I Like or a Job I Can Get: Designing Job Recommender Systems Using Field Experiments
di: Bied, Guillaume, et al.
Pubblicazione: (2026)

Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification
di: Cohen, Eyal, et al.
Pubblicazione: (2025)

Provably Accurate Shapley Value Estimation via Leverage Score Sampling
di: Musco, Christopher, et al.
Pubblicazione: (2024)

Provably Reliable Classifier Guidance via Cross-Entropy Control
di: Sahu, Sharan, et al.
Pubblicazione: (2026)

Extrapolation in Statistical Learning with Extreme Value Theory
di: Engelke, Sebastian, et al.
Pubblicazione: (2026)

Labels in Extremes: How Well Calibrated are Extreme Multi-label Classifiers?
di: Ullah, Nasib, et al.
Pubblicazione: (2024)

OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
di: Jiang, Liangze, et al.
Pubblicazione: (2024)

MetaOOD: Automatic Selection of OOD Detection Models
di: Qin, Yuehan, et al.
Pubblicazione: (2024)

Provable Unrestricted Adversarial Training without Compromise with Generalizability
di: Zhang, Lilin, et al.
Pubblicazione: (2023)

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

M3OOD: Automatic Selection of Multimodal OOD Detectors
di: Qin, Yuehan, et al.
Pubblicazione: (2025)

Adversarial Attacks in Weight-Space Classifiers
di: Shor, Tamir, et al.
Pubblicazione: (2025)

Adversarial Attacks and Dimensionality in Text Classifiers
di: Chattopadhyay, Nandish, et al.
Pubblicazione: (2024)

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

Provably Adaptive Linear Approximation for the Shapley Value and Beyond
di: Li, Weida, et al.
Pubblicazione: (2026)

Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier
di: Frank, Natalie S.
Pubblicazione: (2024)

Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data
di: Mondal, Sudeepta, et al.
Pubblicazione: (2026)

Adversarial Machine Learning: Attacking and Safeguarding Image Datasets
di: Chowdhury, Koushik
Pubblicazione: (2025)

Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
di: Yu, Xudong, et al.
Pubblicazione: (2024)

Fairness Testing through Extreme Value Theory
di: Monjezi, Verya, et al.
Pubblicazione: (2025)

DCILP: A Distributed Approach for Large-Scale Causal Structure Learning
di: Dong, Shuyu, et al.
Pubblicazione: (2024)

Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach
di: Chen, Xuyang, et al.
Pubblicazione: (2025)

GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model
di: Xu, Haoyan, et al.
Pubblicazione: (2025)

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

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

Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models
di: Shen, Xu, et al.
Pubblicazione: (2024)

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
di: Lu, Ziqing, et al.
Pubblicazione: (2025)

Detecting OOD Samples via Optimal Transport Scoring Function
di: Gao, Heng, et al.
Pubblicazione: (2025)

On the Generalization of Adversarially Trained Quantum Classifiers
di: Georgiou, Petros, et al.
Pubblicazione: (2025)

On the Effectiveness of Adversarial Training on Malware Classifiers
di: Bostani, Hamid, et al.
Pubblicazione: (2024)

Classifying Overlapping Gaussian Mixtures in High Dimensions: From Optimal Classifiers to Neural Nets
di: Cohen, Khen, et al.
Pubblicazione: (2024)

Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation
di: Li, Shangzhe, et al.
Pubblicazione: (2026)

Extreme-value forest fire prediction A study of the Loss Function in an Ordinality Scheme
di: Caron, Nicolas, et al.
Pubblicazione: (2026)