Copertina

Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassifications

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Capelli, Lorenzo, Rosa, Leandro de Souza, Setti, Gianluca, Mangia, Mauro, Rovatti, Riccardo
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off
di: Enttsel, Andriy, et al.
Pubblicazione: (2025)

On-board Telemetry Monitoring in Autonomous Satellites: Challenges and Opportunities
di: Capelli, Lorenzo, et al.
Pubblicazione: (2026)

Anomaly Detection based on Compressed Data: an Information Theoretic Characterization
di: Marchioni, Alex, et al.
Pubblicazione: (2021)

Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression
di: Nikiforos, Lorenzo, et al.
Pubblicazione: (2025)

CORE: Robust Out-of-Distribution Detection via Confidence and Orthogonal Residual Scoring
di: Yang, Jin Mo, et al.
Pubblicazione: (2026)

Generative Adversarial Evasion and Out-of-Distribution Detection for UAV Cyber-Attacks
di: Panda, Deepak Kumar, et al.
Pubblicazione: (2025)

Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics
di: Flores, Lorenzo Jaime Yu, et al.
Pubblicazione: (2025)

Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
di: Yamada, Daisuke, et al.
Pubblicazione: (2025)

Distributional Uncertainty for Out-of-Distribution Detection
di: Kim, JinYoung, et al.
Pubblicazione: (2025)

Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments
di: Lee, Heeyoung, et al.
Pubblicazione: (2024)

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
di: Gao, Xin, et al.
Pubblicazione: (2025)

On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models
di: Yang, April, et al.
Pubblicazione: (2024)

ExDD: Explicit Dual Distribution Learning for Surface Defect Detection via Diffusion Synthesis
di: Aqeel, Muhammad, et al.
Pubblicazione: (2025)

Score-based Conditional Out-of-Distribution Augmentation for Graph Covariate Shift
di: Wang, Bohan, et al.
Pubblicazione: (2024)

Goal-Oriented Joint Source-Channel Coding: Distortion-Classification-Power Trade-off
di: Enttsel, Andriy, et al.
Pubblicazione: (2025)

DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection
di: Aljaafari, Tala, et al.
Pubblicazione: (2025)

Face Reconstruction Transfer Attack as Out-of-Distribution Generalization
di: Jung, Yoon Gyo, et al.
Pubblicazione: (2024)

Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks
di: Kazoom, Roie, et al.
Pubblicazione: (2024)

Learning Multi-Manifold Embedding for Out-Of-Distribution Detection
di: Li, Jeng-Lin, et al.
Pubblicazione: (2024)

Probabilistic Trust Intervals for Out of Distribution Detection
di: Singh, Gagandeep, et al.
Pubblicazione: (2021)

Out-of-Distribution Detection using Counterfactual Distance
di: Stoica, Maria, et al.
Pubblicazione: (2025)

An Unsupervised Adversarial Autoencoder for Cyber Attack Detection in Power Distribution Grids
di: Zideh, Mehdi Jabbari, et al.
Pubblicazione: (2024)

Neural Distribution Prior for LiDAR Out-of-Distribution Detection
di: Li, Zizhao, et al.
Pubblicazione: (2026)

Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems
di: Hodge, Victoria J., et al.
Pubblicazione: (2025)

Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion
di: Li, Jiawei, et al.
Pubblicazione: (2024)

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
di: Kim, Kangsan, et al.
Pubblicazione: (2024)

Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks
di: Soltani, Nasim, et al.
Pubblicazione: (2026)

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection
di: Nasvytis, Linas, et al.
Pubblicazione: (2024)

MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
di: Dong, Hao, et al.
Pubblicazione: (2024)

Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble
di: Xu, Chenhui, et al.
Pubblicazione: (2024)

DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection
di: Caetano, Francisco, et al.
Pubblicazione: (2025)

Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendation
di: Zhao, Chu, et al.
Pubblicazione: (2025)

Unsupervised Transcript-assisted Video Summarization and Highlight Detection
di: Barbakos, Spyros, et al.
Pubblicazione: (2025)

Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning
di: Rossolini, Giulio, et al.
Pubblicazione: (2025)

Hide and Find: A Distributed Adversarial Attack on Federated Graph Learning
di: Liu, Jinshan, et al.
Pubblicazione: (2026)

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
di: Duan, Tianyang, et al.
Pubblicazione: (2025)

Adversarial Attacks to Latent Representations of Distributed Neural Networks in Split Computing
di: Zhang, Milin, et al.
Pubblicazione: (2023)

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
di: Franzmeyer, Tim, et al.
Pubblicazione: (2022)

Exploiting Diffusion Prior for Out-of-Distribution Detection
di: Zhu, Armando, et al.
Pubblicazione: (2024)

From Out-of-Distribution Detection to Hallucination Detection: A Geometric View
di: Liu, Litian, et al.
Pubblicazione: (2026)