Copertina

Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Shengchao, Liu, Xiaoming, Wang, Yichen, Cheng, Zehua, Li, Chengzhengxu, Zhang, Zhaohan, Lan, Yu, Shen, Chao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment
di: Liu, Shengchao, et al.
Pubblicazione: (2025)

Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
di: Li, Chengzhengxu, et al.
Pubblicazione: (2024)

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
di: Li, Chengzhengxu, et al.
Pubblicazione: (2025)

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

DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection
di: Ma, Guoxin, et al.
Pubblicazione: (2025)

StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation
di: Liu, Xiaoming, et al.
Pubblicazione: (2024)

MGTEVAL: An Interactive Platform for Systemtic Evaluation of Machine-Generated Text Detectors
di: Li, Yuanfan, et al.
Pubblicazione: (2026)

Confidence Should Be Calibrated More Than One Turn Deep
di: Zhang, Zhaohan, et al.
Pubblicazione: (2026)

Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning
di: Li, Chengzhengxu, et al.
Pubblicazione: (2023)

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
di: Fan, Ziqing, et al.
Pubblicazione: (2024)

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation
di: Wang, Yibo, et al.
Pubblicazione: (2025)

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
di: Bao, Guangsheng, et al.
Pubblicazione: (2023)

Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack
di: Huang, Tiansheng, et al.
Pubblicazione: (2024)

Contrasting Adversarial Perturbations: The Space of Harmless Perturbations
di: Chen, Lu, et al.
Pubblicazione: (2024)

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
di: Singh, Naman Deep, et al.
Pubblicazione: (2024)

Improving the Robustness of Large Language Models for Code Tasks via Fine-tuning with Perturbed Data
di: Liu, Yang, et al.
Pubblicazione: (2026)

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
di: Huang, Tiansheng, et al.
Pubblicazione: (2024)

Speculative Coreset Selection for Task-Specific Fine-tuning
di: Zhang, Xiaoyu, et al.
Pubblicazione: (2024)

Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
di: Wang, Dongwei, et al.
Pubblicazione: (2024)

Fine-tuning ChatGPT for Automatic Scoring of Written Scientific Explanations in Chinese
di: Yang, Jie, et al.
Pubblicazione: (2025)

A Mimetic Detector for Adversarial Image Perturbations
di: Corbino, Johnny
Pubblicazione: (2026)

HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring
di: Su, Zhixiong, et al.
Pubblicazione: (2025)

Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners
di: Liu, Mushui, et al.
Pubblicazione: (2024)

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

Noise Supervised Contrastive Learning and Feature-Perturbed for Anomalous Sound Detection
di: Huang, Shun, et al.
Pubblicazione: (2025)

Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations
di: Mi, Zhendong, et al.
Pubblicazione: (2025)

Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
di: Wang, Yichen, et al.
Pubblicazione: (2024)

GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models
di: Zhang, Zhaohan, et al.
Pubblicazione: (2025)

Explaining Time Series via Contrastive and Locally Sparse Perturbations
di: Liu, Zichuan, et al.
Pubblicazione: (2024)

Perturbation-Assisted Sample Synthesis: A Novel Approach for Uncertainty Quantification
di: Liu, Yifei, et al.
Pubblicazione: (2023)

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement
di: Dong, Yichen, et al.
Pubblicazione: (2025)

Consistency of Lloyd's Algorithm Under Perturbations
di: Patel, Dhruv, et al.
Pubblicazione: (2023)

Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
di: Yuan, Xinyu, et al.
Pubblicazione: (2026)

PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
di: Lu, Junjian, et al.
Pubblicazione: (2024)

How would Stance Detection Techniques Evolve after the Launch of ChatGPT?
di: Zhang, Bowen, et al.
Pubblicazione: (2022)

Asymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation
di: Xie, Yiling, et al.
Pubblicazione: (2024)

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations
di: Wang, Chao, et al.
Pubblicazione: (2023)

Perturbing the principal Dirichlet eigenfunction
di: Chao, Brian, et al.
Pubblicazione: (2025)

Singular Perturbation: When the Perturbation Parameter Becomes a State-Dependent Function
di: Liu, Tengfei, et al.
Pubblicazione: (2024)

ValueFlow: Measuring the Propagation of Value Perturbations in Multi-Agent LLM Systems
di: Liu, Jinnuo, et al.
Pubblicazione: (2026)