Buchumschlag

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Vu, Kiana, Lai, Phung, Nguyen, Truc
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

From Black Box to Insight: Explainable AI for Extreme Event Preparedness
von: Vu, Kiana, et al.
Veröffentlicht: (2025)

Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation
von: Zhao, Ke, et al.
Veröffentlicht: (2024)

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing
von: Zhong, Xuyang, et al.
Veröffentlicht: (2025)

Detection of False Data Injection Attacks (FDIA) on Power Dynamical Systems With a State Prediction Method
von: Sahu, Abhijeet, et al.
Veröffentlicht: (2024)

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
von: Samandarov, Samandar, et al.
Veröffentlicht: (2026)

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
von: Winninger, Thomas, et al.
Veröffentlicht: (2025)

Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
von: Lin, Fudong, et al.
Veröffentlicht: (2025)

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

BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks
von: Shin, Woojin, et al.
Veröffentlicht: (2024)

Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model
von: Mitra, Sinjini, et al.
Veröffentlicht: (2026)

Vision Transformer with Adversarial Indicator Token against Adversarial Attacks in Radio Signal Classifications
von: Zhang, Lu, et al.
Veröffentlicht: (2025)

Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
von: Xian, Guanmeng, et al.
Veröffentlicht: (2026)

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

Enhancing Time Series Forecasting via a Parallel Hybridization of ARIMA and Polynomial Classifiers
von: Nguyen, Thanh Son, et al.
Veröffentlicht: (2025)

Generating Universal Adversarial Perturbations for Quantum Classifiers
von: Anil, Gautham, et al.
Veröffentlicht: (2024)

Fuzzy Logic Function as a Post-hoc Explanator of the Nonlinear Classifier
von: Klimo, Martin, et al.
Veröffentlicht: (2024)

SSET: Swapping-Sliding Explanation for Time Series Classifiers in Affect Detection
von: Fouladgar, Nazanin, et al.
Veröffentlicht: (2024)

rSDNet: Unified Robust Neural Learning against Label Noise and Adversarial Attacks
von: Jana, Suryasis, et al.
Veröffentlicht: (2026)

Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning
von: Kim, Taejin, et al.
Veröffentlicht: (2023)

Angular Steering: Behavior Control via Rotation in Activation Space
von: Vu, Hieu M., et al.
Veröffentlicht: (2025)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models
von: Do, Nguyen, et al.
Veröffentlicht: (2025)

Explanation-Guided Adversarial Training for Robust and Interpretable Models
von: Chen, Chao, et al.
Veröffentlicht: (2026)

Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
von: Bley, Florian, et al.
Veröffentlicht: (2025)

Adversarial Attacks on Hyperbolic Networks
von: van Spengler, Max, et al.
Veröffentlicht: (2024)

Certified Robustness against Sparse Adversarial Perturbations via Data Localization
von: Pal, Ambar, et al.
Veröffentlicht: (2024)

Fairness of Classifiers in the Presence of Constraints between Features
von: Cooper, Martin C., et al.
Veröffentlicht: (2026)

GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization
von: Yang, Xiaodong, et al.
Veröffentlicht: (2024)

SHAP-based Explanations are Sensitive to Feature Representation
von: Hwang, Hyunseung, et al.
Veröffentlicht: (2025)

Feature-level Interaction Explanations in Multimodal Transformers
von: Kim, Yeji, et al.
Veröffentlicht: (2026)

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
von: Yuan, Leitao, et al.
Veröffentlicht: (2026)

Machine-learned Adversarial Attacks against Fault Prediction Systems in Smart Electrical Grids
von: Ardito, Carmelo, et al.
Veröffentlicht: (2023)

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

A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures
von: Nguyen, Thanh Tam, et al.
Veröffentlicht: (2024)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
von: Nguyen, Thanh, et al.
Veröffentlicht: (2024)

TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Data
von: He, Zhipeng, et al.
Veröffentlicht: (2025)

How to Protect Models against Adversarial Unlearning?
von: Jasiorski, Patryk, et al.
Veröffentlicht: (2025)

ROKA: Robust Knowledge Unlearning against Adversaries
von: Shin, Jinmyeong, et al.
Veröffentlicht: (2026)

CAFO: Feature-Centric Explanation on Time Series Classification
von: Kim, Jaeho, et al.
Veröffentlicht: (2024)

FLEX: Feature Importance from Layered Counterfactual Explanations
von: Keshtmand, Nawid, et al.
Veröffentlicht: (2025)

Adversarial Attacks Leverage Interference Between Features in Superposition
von: Stevinson, Edward, et al.
Veröffentlicht: (2025)