Buchumschlag

SHLIME: Foiling adversarial attacks fooling SHAP and LIME

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chauhan, Sam, Duguet, Estelle, Ramakrishnan, Karthik, Van Deventer, Hugh, Kruger, Jack, Subbaraman, Ranjan
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Nonideality-aware training makes memristive networks more robust to adversarial attacks
von: Joksas, Dovydas, et al.
Veröffentlicht: (2024)

Trainwreck: A damaging adversarial attack on image classifiers
von: Zahálka, Jan
Veröffentlicht: (2023)

On the existence of consistent adversarial attacks in high-dimensional linear classification
von: Vilucchio, Matteo, et al.
Veröffentlicht: (2025)

Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks
von: Pizarro, Matías, et al.
Veröffentlicht: (2026)

Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensemble
von: Xue, Yunzhe, et al.
Veröffentlicht: (2024)

RAB$^2$-DEF: Dynamic and explainable defense against adversarial attacks in Federated Learning to fair poor clients
von: Rodríguez-Barroso, Nuria, et al.
Veröffentlicht: (2024)

Visually Analyze SHAP Plots to Diagnose Misclassifications in ML-based Intrusion Detection
von: Mia, Maraz, et al.
Veröffentlicht: (2024)

Explainable Threat Attribution for IoT Networks Using Conditional SHAP and Flow Behavior Modelling
von: Ozechi, Samuel, et al.
Veröffentlicht: (2026)

Fooling SHAP with Output Shuffling Attacks
von: Yuan, Jun, et al.
Veröffentlicht: (2024)

Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model
von: Todisco, Massimiliano, et al.
Veröffentlicht: (2024)

Correlation inference attacks against machine learning models
von: Creţu, Ana-Maria, et al.
Veröffentlicht: (2021)

A novel reliability attack of Physical Unclonable Functions
von: Li, Gaoxiang, et al.
Veröffentlicht: (2024)

AED: An black-box NLP classifier model attacker
von: Liu, Yueyang, et al.
Veröffentlicht: (2021)

Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks
von: Kapoor, Sourabh, et al.
Veröffentlicht: (2024)

Power side-channel leakage localization through adversarial training of deep neural networks
von: Gammell, Jimmy, et al.
Veröffentlicht: (2024)

Robustness bounds on the successful adversarial examples in probabilistic models: Implications from Gaussian processes
von: Maeshima, Hiroaki, et al.
Veröffentlicht: (2024)

Noisy Neighbors: Efficient membership inference attacks against LLMs
von: Galli, Filippo, et al.
Veröffentlicht: (2024)

Embedding-based classifiers can detect prompt injection attacks
von: Ayub, Md. Ahsan, et al.
Veröffentlicht: (2024)

Evaluating lightweight unsupervised online IDS for masquerade attacks in CAN
von: Moriano, Pablo, et al.
Veröffentlicht: (2024)

Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre
von: Carlini, Nicholas
Veröffentlicht: (2024)

Virtual camera detection: Catching video injection attacks in remote biometric systems
von: Kurmankhojayev, Daniyar, et al.
Veröffentlicht: (2025)

A clean-label graph backdoor attack method in node classification task
von: Xing, Xiaogang, et al.
Veröffentlicht: (2023)

AlertBERT: A noise-robust alert grouping framework for simultaneous cyber attacks
von: Karner, Lukas, et al.
Veröffentlicht: (2026)

D2R: dual regularization loss with collaborative adversarial generation for model robustness
von: Liu, Zhenyu, et al.
Veröffentlicht: (2025)

BLIA: Detect model memorization in binary classification model through passive Label Inference attack
von: Khan, Mohammad Wahiduzzaman, et al.
Veröffentlicht: (2025)

A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack
von: Preen, Richard J., et al.
Veröffentlicht: (2025)

Anticipated Network Surveillance -- An extrapolated study to predict cyber-attacks using Machine Learning and Data Analytics
von: Srivastava, Aviral, et al.
Veröffentlicht: (2023)

Enhancing the Robustness of QMIX against State-adversarial Attacks
von: Guo, Weiran, et al.
Veröffentlicht: (2023)

New intelligent defense systems to reduce the risks of Selfish Mining and Double-Spending attacks using Learning Automata
von: Ghoreishi, Seyed Ardalan, et al.
Veröffentlicht: (2023)

Anomaly Detection in OKTA Logs using Autoencoders
von: Cain, Jericho, et al.
Veröffentlicht: (2024)

Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling
von: Srisumrith, Norrakith, et al.
Veröffentlicht: (2026)

Robust LLM safeguarding via refusal feature adversarial training
von: Yu, Lei, et al.
Veröffentlicht: (2024)

Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images
von: Rasaee, Hamza, et al.
Veröffentlicht: (2021)

On the use of neurosymbolic AI for defending against cyber attacks
von: Grov, Gudmund, et al.
Veröffentlicht: (2024)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
von: Carlini, Nicholas, et al.
Veröffentlicht: (2025)

Conti Inc.: Understanding the Internal Discussions of a large Ransomware-as-a-Service Operator with Machine Learning
von: Ruellan, Estelle, et al.
Veröffentlicht: (2023)

Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy
von: Krüger, Fabian P., et al.
Veröffentlicht: (2024)

Comparing privacy notions for protection against reconstruction attacks in machine learning
von: Biswas, Sayan, et al.
Veröffentlicht: (2025)

Exploring the limits of strong membership inference attacks on large language models
von: Hayes, Jamie, et al.
Veröffentlicht: (2025)

UserBoost: Generating User-specific Synthetic Data for Faster Enrolment into Behavioural Biometric Systems
von: Webber, George, et al.
Veröffentlicht: (2024)