Imagen de Portada

Adversarial Attacks on AI-Generated Text Detection Models: A Token Probability-Based Approach Using Embeddings

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kadhim, Ahmed K., Jiao, Lei, Shafik, Rishad, Granmo, Ole-Christoffer
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Scalable Multi-phase Word Embedding Using Conjunctive Propositional Clauses
por: Kadhim, Ahmed K., et al.
Publicado: (2025)

Exploring State Space and Reasoning by Elimination in Tsetlin Machines
por: Kadhim, Ahmed K., et al.
Publicado: (2024)

Omni TM-AE: A Scalable and Interpretable Embedding Model Using the Full Tsetlin Machine State Space
por: Kadhim, Ahmed K., et al.
Publicado: (2025)

FastOmniTMAE: Parallel Clause Learning for Scalable and Hardware-Efficient Tsetlin Embeddings
por: Kadhim, Ahmed K., et al.
Publicado: (2026)

A Methodology for Transparent Logic-Based Classification Using a Multi-Task Convolutional Tsetlin Machine
por: Shende, Mayur Kishor, et al.
Publicado: (2025)

An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Accelerator
por: Tunheim, Svein Anders, et al.
Publicado: (2025)

Uncertainty Quantification in the Tsetlin Machine
por: Helin, Runar, et al.
Publicado: (2025)

Scalable Bayesian Network Structure Learning Using Tsetlin Machine to Constrain the Search Space
por: Dumbre, Kunal, et al.
Publicado: (2025)

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations
por: Teja, Lekkala Sai, et al.
Publicado: (2025)

Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines
por: Halenka, Vojtech, et al.
Publicado: (2024)

ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection
por: Huang, Fan, et al.
Publicado: (2024)

An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites
por: Grønningsæter, Ylva, et al.
Publicado: (2024)

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
por: Chen, Kexin, et al.
Publicado: (2025)

Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach
por: Quevedo, Ernesto, et al.
Publicado: (2024)

Understanding Token Probability Encoding in Output Embeddings
por: Cho, Hakaze, et al.
Publicado: (2024)

A Generative Adversarial Attack for Multilingual Text Classifiers
por: Roth, Tom, et al.
Publicado: (2024)

Robust AI-Generated Text Detection by Restricted Embeddings
por: Kuznetsov, Kristian, et al.
Publicado: (2024)

AI Generated Text Detection Using Instruction Fine-tuned Large Language and Transformer-Based Models
por: Guggilla, Chinnappa, et al.
Publicado: (2025)

A Multi-Strategy Approach for AI-Generated Text Detection
por: Zain, Ali, et al.
Publicado: (2025)

Vietnamese AI Generated Text Detection
por: Tran, Quang-Dan, et al.
Publicado: (2024)

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
por: Huang, Guanhua, et al.
Publicado: (2024)

A Lightweight Approach to Detection of AI-Generated Texts Using Stylometric Features
por: Aityan, Sergey K., et al.
Publicado: (2025)

Enhancing Text Authenticity: A Novel Hybrid Approach for AI-Generated Text Detection
por: Zhang, Ye, et al.
Publicado: (2024)

On-Device Interpretable Tsetlin Machine-Based Intrusion Detection for Secure IoMT
por: Jaiswal, Rahul, et al.
Publicado: (2026)

TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
por: Lu, Pengqian, et al.
Publicado: (2025)

A Tsetlin Machine-driven Intrusion Detection System for Next-Generation IoMT Security
por: Jaiswal, Rahul, et al.
Publicado: (2026)

AI Generated Text Detection
por: Alikhanov, Adilkhan, et al.
Publicado: (2026)

The Arabic AI Fingerprint: Stylometric Analysis and Detection of Large Language Models Text
por: Al-Shaibani, Maged S., et al.
Publicado: (2025)

Explainability-Based Token Replacement on LLM-Generated Text
por: Mohammadi, Hadi, et al.
Publicado: (2025)

AI-Based Clinical Rule Discovery for NMIBC Recurrence through Tsetlin Machines
por: Abbas, Saram, et al.
Publicado: (2025)

A Comparative Study of Feature Selection in Tsetlin Machines
por: Halenka, Vojtech, et al.
Publicado: (2025)

On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
por: Guo, Yikai, et al.
Publicado: (2026)

Detecting the Machine: A Comprehensive Benchmark of AI-Generated Text Detectors Across Architectures, Domains, and Adversarial Conditions
por: Baidya, Madhav S., et al.
Publicado: (2026)

OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
por: Lewoniewski, Włodzimierz, et al.
Publicado: (2024)

Fine-Grained Detection of AI-Generated Text Using Sentence-Level Segmentation
por: Teja, Lekkala Sai, et al.
Publicado: (2025)

Bagging-Based Model Merging for Robust General Text Embeddings
por: Zhang, Hengran, et al.
Publicado: (2026)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
por: Mu, Junjie, et al.
Publicado: (2025)

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
por: Liu, Han, et al.
Publicado: (2024)

SwiftEmbed: Ultra-Fast Text Embeddings via Static Token Lookup for Real-Time Applications
por: Lansiaux, Edouard, et al.
Publicado: (2025)

Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation
por: Shahariar, G M, et al.
Publicado: (2024)