Copertina

Towards Robust Universal Perturbation Attacks: A Float-Coded, Penalty-Driven Evolutionary Approach

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Shiqi, Khosravy, Mahdi, Gupta, Neeraj, Witkowski, Olaf
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Robust Content Watermarking Against Removal and Forgery Attacks
di: Zhu, Yifan, et al.
Pubblicazione: (2026)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
di: Ying, Chengyang, et al.
Pubblicazione: (2022)

Toward Inherently Robust VLMs Against Visual Perception Attacks
di: MohajerAnsari, Pedram, et al.
Pubblicazione: (2025)

Towards Robust Nonlinear Subspace Clustering: A Kernel Learning Approach
di: Xu, Kunpeng, et al.
Pubblicazione: (2025)

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification
di: Pellicer, Alvaro Lopez, et al.
Pubblicazione: (2024)

Boosting Adversarial Transferability via Residual Perturbation Attack
di: Peng, Jinjia, et al.
Pubblicazione: (2025)

Lipschitz-Based Robustness Certification Under Floating-Point Execution
di: Murray, Toby
Pubblicazione: (2026)

Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
di: Jiang, Shiyi, et al.
Pubblicazione: (2025)

Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition
di: Kong, Weizhe, et al.
Pubblicazione: (2025)

Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
di: Hu, Xuran, et al.
Pubblicazione: (2024)

Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
di: Wang, Zheng, et al.
Pubblicazione: (2025)

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
di: Sun, Changchang, et al.
Pubblicazione: (2024)

Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment
di: Moradinasab, Nazanin, et al.
Pubblicazione: (2025)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
di: Zhang, Yechao, et al.
Pubblicazione: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
di: Cui, Kaiyuan, et al.
Pubblicazione: (2026)

Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks
di: Zhang, Lei, et al.
Pubblicazione: (2024)

Towards Adversarially Robust Dataset Distillation by Curvature Regularization
di: Xue, Eric, et al.
Pubblicazione: (2024)

Towards Large Model Feature Coding
di: Pang, Youwei, et al.
Pubblicazione: (2026)

Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
di: Zhuang, Weiwei, et al.
Pubblicazione: (2026)

Beyond Full Poisoning: Effective Availability Attacks with Partial Perturbation
di: Zhe, Yu, et al.
Pubblicazione: (2024)

Unlearning Concepts from Text-to-Video Diffusion Models
di: Liu, Shiqi, et al.
Pubblicazione: (2024)

Universal Camouflage Attack on Vision-Language Models for Autonomous Driving
di: Kong, Dehong, et al.
Pubblicazione: (2025)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
di: Lian, Jiawei, et al.
Pubblicazione: (2024)

FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search
di: Dotzel, Jordan, et al.
Pubblicazione: (2023)

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
di: Hu, Hanjiang, et al.
Pubblicazione: (2023)

Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models
di: Yan, YangTian, et al.
Pubblicazione: (2025)

LogiCode: an LLM-Driven Framework for Logical Anomaly Detection
di: Zhang, Yiheng, et al.
Pubblicazione: (2024)

Towards Class-wise Robustness Analysis
di: Medi, Tejaswini, et al.
Pubblicazione: (2024)

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
di: Liu, Zhenyu, et al.
Pubblicazione: (2024)

Universal Backdoor Attacks
di: Schneider, Benjamin, et al.
Pubblicazione: (2023)

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

Detecting Adversarial Data using Perturbation Forgery
di: Wang, Qian, et al.
Pubblicazione: (2024)

GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective
di: Wang, Xu, et al.
Pubblicazione: (2026)

Towards Desiderata-Driven Design of Visual Counterfactual Explainers
di: Bender, Sidney, et al.
Pubblicazione: (2025)

Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts
di: Gupta, Madhav, et al.
Pubblicazione: (2025)

Training Image Derivatives: Increased Accuracy and Universal Robustness
di: Avrutskiy, Vsevolod I.
Pubblicazione: (2023)

DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation
di: Wang, Yunjuan, et al.
Pubblicazione: (2024)

Universal and Transferable Attacks on Pathology Foundation Models
di: Wang, Yuntian, et al.
Pubblicazione: (2025)

Generated Contents Enrichment
di: Naseri, Mahdi, et al.
Pubblicazione: (2024)

Prompting Forgetting: Unlearning in GANs via Textual Guidance
di: Nagasubramaniam, Piyush, et al.
Pubblicazione: (2025)