Cover Image

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Teja, Lekkala Sai, Yadagiri, Annepaka, Anish, Sangam Sai, Nuthakki, Siva Gopala Krishna, Pakray, Partha
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Mixture of Detectors: A Compact View of Machine-Generated Text Detection
by: Lekkala, Sai Teja, et al.
Published: (2025)

Adversarial Text Generation with Dynamic Contextual Perturbation
by: Waghela, Hetvi, et al.
Published: (2025)

CivicShield: A Cross-Domain Defense-in-Depth Framework for Securing Government-Facing AI Chatbots Against Multi-Turn Adversarial Attacks
by: Patil, KrishnaSaiReddy
Published: (2026)

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
by: Kadali, Sri Durga Sai Sowmya, et al.
Published: (2026)

Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack
by: Zhou, Ying, et al.
Published: (2024)

Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training
by: Li, Yuanfan, et al.
Published: (2025)

The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
by: Makroo, Owais, et al.
Published: (2025)

Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences
by: Zhang, Yangshijie
Published: (2025)

RAGShield: Detecting Numerical Claim Manipulation in Government RAG Systems
by: Patil, KrishnaSaiReddy
Published: (2026)

Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent
by: Waghela, Hetvi, et al.
Published: (2024)

Fight Poison with Poison: Enhancing Robustness in Few-shot Machine-Generated Text Detection with Adversarial Training
by: Duan, Wenjing, et al.
Published: (2026)

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
by: Zhang, Xinyu, et al.
Published: (2023)

A Modified Word Saliency-Based Adversarial Attack on Text Classification Models
by: Waghela, Hetvi, et al.
Published: (2024)

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
by: Mangaokar, Neal, et al.
Published: (2024)

Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
by: Fang, Junyuan, et al.
Published: (2025)

DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution
by: Teja, L. D. M. S. Sai, et al.
Published: (2025)

Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods
by: Dey, Roopkatha, et al.
Published: (2024)

TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
by: Cao, Xi, et al.
Published: (2024)

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

On Evaluating The Performance of Watermarked Machine-Generated Texts Under Adversarial Attacks
by: Liu, Zesen, et al.
Published: (2024)

LLMs for Cyber Security: New Opportunities
by: Divakaran, Dinil Mon, et al.
Published: (2024)

Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models
by: Liu, Xiao, et al.
Published: (2024)

IslandRun: Privacy-Aware Multi-Objective Orchestration for Distributed AI Inference
by: Malepati, Bala Siva Sai Akhil
Published: (2025)

Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model
by: Cao, Xi, et al.
Published: (2024)

AI-Driven Cybersecurity Threats: A Survey of Emerging Risks and Defensive Strategies
by: Erukude, Sai Teja, et al.
Published: (2026)

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy
by: Fu, Yu, et al.
Published: (2023)

The Aegis Protocol: A Foundational Security Framework for Autonomous AI Agents
by: Adapala, Sai Teja Reddy, et al.
Published: (2025)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
by: Kim, Hee-Seon, et al.
Published: (2024)

SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems
by: Patil, KrishnaSaiReddy
Published: (2026)

Automated Generation of Accurate Privacy Captions From Android Source Code Using Large Language Models
by: Jain, Vijayanta, et al.
Published: (2026)

Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents
by: Narajala, Vineeth Sai, et al.
Published: (2025)

Fast Plaintext-Ciphertext Matrix Multiplication from Additively Homomorphic Encryption
by: Ramapragada, Krishna Sai Tarun, et al.
Published: (2025)

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
by: Hossen, Md Imran, et al.
Published: (2024)

MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction
by: Hu, Xiao, et al.
Published: (2025)

Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions
by: Thota, Poojitha, et al.
Published: (2024)

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models
by: Huo, Mingjia, et al.
Published: (2024)

Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script
by: Cao, Xi, et al.
Published: (2024)

Complete Evasion, Zero Modification: PDF Attacks on AI Text Detection
by: Creo, Aldan
Published: (2025)

Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections
by: Maloyan, Narek, et al.
Published: (2025)