Copertina

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Fakorede, Olukorede, Atsague, Modeste, Tian, Jin
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness
di: Fakorede, Olukorede, et al.
Pubblicazione: (2024)

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
di: Oskouie, Haniyeh Ehsani, et al.
Pubblicazione: (2022)

The Impact of Scaling Training Data on Adversarial Robustness
di: Zimmerli, Marco, et al.
Pubblicazione: (2025)

Improving the Transferability of Adversarial Attacks by an Input Transpose
di: Wan, Qing, et al.
Pubblicazione: (2025)

Vulnerability analysis of captcha using Deep learning
di: Walia, Jaskaran Singh, et al.
Pubblicazione: (2023)

Towards Understanding Dual BN In Hybrid Adversarial Training
di: Zhang, Chenshuang, et al.
Pubblicazione: (2024)

Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
di: Yin, Minglei, et al.
Pubblicazione: (2023)

Efficient Semi-Supervised Adversarial Training via Latent Clustering-Based Data Reduction
di: Ghosh, Somrita, et al.
Pubblicazione: (2025)

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

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
di: Guan, Jiwei, et al.
Pubblicazione: (2026)

Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume
di: Guo, Ping, et al.
Pubblicazione: (2024)

Rewriting the Budget: A General Framework for Black-Box Attacks Under Cost Asymmetry
di: Salmani, Mahdi, et al.
Pubblicazione: (2025)

Representation Magnitude has a Liability to Privacy Vulnerability
di: Fang, Xingli, et al.
Pubblicazione: (2024)

Verification of Neural Networks against Convolutional Perturbations via Parameterised Kernels
di: Brückner, Benedikt, et al.
Pubblicazione: (2024)

Towards Robust Protective Perturbation against DeepFake Face Swapping
di: Yao, Hengyang, et al.
Pubblicazione: (2025)

Adversarial Detection by Approximation of Ensemble Boundary
di: Windeatt, T.
Pubblicazione: (2022)

Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples
di: Tsigos, Konstantinos, et al.
Pubblicazione: (2025)

GLEAN: Generative Learning for Eliminating Adversarial Noise
di: Kim, Justin Lyu, et al.
Pubblicazione: (2024)

On the Importance of Backbone to the Adversarial Robustness of Object Detectors
di: Li, Xiao, et al.
Pubblicazione: (2023)

Fingerprinting Image-to-Image Generative Adversarial Networks
di: Li, Guanlin, et al.
Pubblicazione: (2021)

Evaluating the Evaluators: Trust in Adversarial Robustness Tests
di: Cinà, Antonio Emanuele, et al.
Pubblicazione: (2025)

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
di: Zou, Yong, et al.
Pubblicazione: (2026)

AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles
di: Salek, M Sabbir, et al.
Pubblicazione: (2023)

Impact of Architectural Modifications on Deep Learning Adversarial Robustness
di: Juraev, Firuz, et al.
Pubblicazione: (2024)

Sy-FAR: Symmetry-based Fair Adversarial Robustness
di: Najjar, Haneen, et al.
Pubblicazione: (2025)

Undermining Image and Text Classification Algorithms Using Adversarial Attacks
di: Lunga, Langalibalele, et al.
Pubblicazione: (2024)

Adversarial attacks and defenses in explainable artificial intelligence: A survey
di: Baniecki, Hubert, et al.
Pubblicazione: (2023)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
di: Kang, Caixin, et al.
Pubblicazione: (2023)

Identifying and Understanding Cross-Class Features in Adversarial Training
di: Wei, Zeming, et al.
Pubblicazione: (2025)

A Survey on Physical Adversarial Attacks against Face Recognition Systems
di: Wang, Mingsi, et al.
Pubblicazione: (2024)

AdvSecureNet: A Python Toolkit for Adversarial Machine Learning
di: Catal, Melih, et al.
Pubblicazione: (2024)

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
di: Basani, Advik Raj, et al.
Pubblicazione: (2024)

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
di: Xie, Yong, et al.
Pubblicazione: (2024)

Pixel Seal: Adversarial-only training for invisible image and video watermarking
di: Souček, Tomáš, et al.
Pubblicazione: (2025)

MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework
di: Guo, Ping, et al.
Pubblicazione: (2025)

Reconstructing Training Data From Real World Models Trained with Transfer Learning
di: Oz, Yakir, et al.
Pubblicazione: (2024)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
di: Wei, Xingxing, et al.
Pubblicazione: (2024)

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
di: Sun, Ye, et al.
Pubblicazione: (2026)

Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
di: Sarkar, Soumyendu, et al.
Pubblicazione: (2025)

Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks
di: Naderi, Hanieh, et al.
Pubblicazione: (2022)