Cover Image

Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rossolini, Giulio, Nesti, Federico, Brau, Fabio, Biondi, Alessandro, Buttazzo, Giorgio
Format:	Preprint
Published:	2022
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications
by: Rossolini, Giulio, et al.
Published: (2023)

CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models
by: Nesti, Federico, et al.
Published: (2022)

Edge-Only Universal Adversarial Attacks in Distributed Learning
by: Rossolini, Giulio, et al.
Published: (2024)

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving
by: Rossolini, Giulio, et al.
Published: (2022)

Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions
by: Pietrosanti, Giulia Marchiori, et al.
Published: (2025)

PairedGTA: Generating Driving Datasets for Controlled Photometric Shift Analysis
by: Chianese, Andrea, et al.
Published: (2026)

Video Deblurring by Sharpness Prior Detection and Edge Information
by: Tian, Yang, et al.
Published: (2025)

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

Learning Robustness at Test-Time from a Non-Robust Teacher
by: Bianchettin, Stefano, et al.
Published: (2026)

OSDaR-AR: Enhancing Railway Perception Datasets via Multi-modal Augmented Reality
by: Nesti, Federico, et al.
Published: (2026)

Increasing the Confidence of Deep Neural Networks by Coverage Analysis
by: Rossolini, Giulio, et al.
Published: (2021)

Towards Railway Domain Adaptation for LiDAR-based 3D Detection: Road-to-Rail and Sim-to-Real via SynDRA-BBox
by: Diaz, Xavier, et al.
Published: (2025)

CORT: Class-Oriented Real-time Tracking for Embedded Systems
by: Cittadini, Edoardo, et al.
Published: (2024)

Integrating Object Detection, LiDAR-Enhanced Depth Estimation, and Segmentation Models for Railway Environments
by: Giannico, Enrico Francesco, et al.
Published: (2026)

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
by: Strack, Lukas, et al.
Published: (2023)

A Comparative Analysis of Visual Odometry in Virtual and Real-World Railways Environments
by: D'Amico, Gianluca, et al.
Published: (2024)

Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
by: Chen, Meng, et al.
Published: (2024)

S2AP: Score-space Sharpness Minimization for Adversarial Pruning
by: Piras, Giorgio, et al.
Published: (2025)

Defending against Patch-Based and Texture-Based Adversarial Attacks with Spectral Decomposition
by: Zhang, Wei, et al.
Published: (2026)

Time Traveling to Defend Against Adversarial Example Attacks in Image Classification
by: Etim, Anthony, et al.
Published: (2024)

Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks
by: Ye, Tian, et al.
Published: (2024)

DataFreeShield: Defending Adversarial Attacks without Training Data
by: Lee, Hyeyoon, et al.
Published: (2024)

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
by: Chen, Ruoxi, et al.
Published: (2021)

Defending Against Frequency-Based Attacks with Diffusion Models
by: Amerehi, Fatemeh, et al.
Published: (2025)

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
by: Guo, Qi, et al.
Published: (2025)

Distillation-Enhanced Physical Adversarial Attacks
by: Liu, Wei, et al.
Published: (2025)

SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
by: Du, Lingyu, et al.
Published: (2025)

LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks
by: Costa, Joana C., et al.
Published: (2025)

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

Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols
by: Cheng, Luo, et al.
Published: (2025)

GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
by: Yang, Yijun, et al.
Published: (2024)

SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
by: Park, Junha, et al.
Published: (2025)

PEPR: Privileged Event-based Predictive Regularization for Domain Generalization
by: Magrini, Gabriele, et al.
Published: (2026)

Visual Adversarial Attacks and Defenses in the Physical World: A Survey
by: Wei, Xingxing, et al.
Published: (2022)

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
by: Piras, Giorgio, et al.
Published: (2024)

Physical Adversarial Attack meets Computer Vision: A Decade Survey
by: Wei, Hui, et al.
Published: (2022)

Towards Physically Realizable Adversarial Attenuation Patch against SAR Object Detection
by: Zhang, Yiming, et al.
Published: (2026)

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
by: Huang, Yao, et al.
Published: (2023)

Adversarial Attacks on Event-Based Pedestrian Detectors: A Physical Approach
by: Lin, Guixu, et al.
Published: (2025)

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
by: Ricci, Simone, et al.
Published: (2024)