Cover Image

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Yinghan, Wen, Juan, Peng, Wanli, Xue, Yiming, Zhang, Ziwei, Wu, Zhengxian
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion
by: Zhou, Yinghan, et al.
Published: (2025)

Is Your Writing Being Mimicked by AI? Unveiling Imitation with Invisible Watermarks in Creative Writing
by: Zhang, Ziwei, et al.
Published: (2025)

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
by: Wu, Zhengxian, et al.
Published: (2025)

GTSD: Generative Text Steganography Based on Diffusion Model
by: Wu, Zhengxian, et al.
Published: (2025)

From Implicit to Explicit: Enhancing Self-Recognition in Large Language Models
by: Zhou, Yinghan, et al.
Published: (2025)

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation
by: Wu, Zhengxian, et al.
Published: (2025)

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
by: Wu, Zhengxian, et al.
Published: (2025)

Generative Text Steganography with Large Language Model
by: Wu, Jiaxuan, et al.
Published: (2024)

EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
by: Wu, Jiaxuan, et al.
Published: (2025)

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
by: Fu, Hang, et al.
Published: (2026)

Upadacitinib in dermatology: ‘Killing’ several diseases with one stone
by: Riccardo Balestri, et al.
Published: (2024)

Infectious disease and endogenous cycles: Lockdown hits two birds with one stone
by: David Desmarchelier, et al.
Published: (2025)

Killing several birds with one stone: A multi‐indication population pharmacokinetic model and Bayesian estimator for enteric‐coated mycophenolate sodium
by: Yeleen Fromage, et al.
Published: (2024)

ImF: Implicit Fingerprint for Large Language Models
by: Wu, Jiaxuan, et al.
Published: (2025)

AI-generated text boundary detection with RoFT
by: Kushnareva, Laida, et al.
Published: (2023)

The perturbation method applied to a robust optimization problem with constraint
by: Luo, Peng, et al.
Published: (2024)

Semi-Riemannian $\text{spin}^c$ manifolds carrying generalized Killing spinors and the classification of Riemannian $\text{spin}^c$ manifolds admitting a type I imaginary generalized Killing spinor
by: Lockman, Samuel
Published: (2025)

Qwen it detect machine-generated text?
by: Marchitan, Teodor-George, et al.
Published: (2025)

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
by: Peng, Wanli, et al.
Published: (2025)

iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
by: Zhang, Chuanrui, et al.
Published: (2025)

Panoptic Diffusion Models: co-generation of images and segmentation maps
by: Long, Yinghan, et al.
Published: (2024)

Humans can learn to detect AI-generated texts, or at least learn when they can't
by: Milička, Jiří, et al.
Published: (2025)

On a generalization of the Johnson-Newman theorem to multiple rank-one perturbations
by: Wang, Wei, et al.
Published: (2025)

People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
by: Russell, Jenna, et al.
Published: (2025)

Multimodal Visual Image Based User Association and Beamforming Using Graph Neural Networks
by: Li, Yinghan, et al.
Published: (2025)

Two birds with one stone: simultaneous realization of both Lunar Coordinate Time and lunar geoid time by a single orbital clock
by: Yang, Tian-Ning, et al.
Published: (2025)

Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection
by: Miralles-González, Pablo, et al.
Published: (2025)

Evaluating perturbation robustness of generative systems that use COBOL code inputs
by: Ackerman, Samuel, et al.
Published: (2025)

Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts
by: Wu, Zongxiao, et al.
Published: (2025)

Machine-generated text detection prevents language model collapse
by: Drayson, George, et al.
Published: (2025)

Large Language Model (LLM) AI text generation detection based on transformer deep learning algorithm
by: Mo, Yuhong, et al.
Published: (2024)

Are generative AI text annotations systematically biased?
by: Stolwijk, Sjoerd B., et al.
Published: (2025)

AI Agent for Reverse-Engineering Legacy Finite-Difference Code and Translating to Devito
by: Hou, Yinghan, et al.
Published: (2026)

Quadratic Killing tensors on symmetric spaces which are not generated by Killing vector fields
by: Matveev, Vladimir S., et al.
Published: (2023)

Prolongation and Killing two-tensors
by: Eastwood, Michael, et al.
Published: (2026)

Towards robust detection of entangled two-photon absorption
by: Pandya, Raj, et al.
Published: (2024)

Cyclization of Short Peptides Designed from Late Embryogenesis Abundant Protein to Improve Stability and Functionality
by: Yinghan Wu, et al.
Published: (2025)

Anchor-MoE: A Mean-Anchored Mixture of Experts For Probabilistic Regression
by: Su, Baozhuo, et al.
Published: (2025)

Relaxing towards generalized one-body Boltzmann states
by: Li, Sheng-Wen, et al.
Published: (2024)

A one‐pot RPA / CRISPR–bio ‐ dCas9 lateral flow assay for rapid and on‐site detection of Monilinia fructicola in stone and pome fruits
by: Li Yang, et al.
Published: (2025)