Copertina

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Naseh, Ali, Mireshghallah, Niloofar
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Position: Privacy Is Not Just Memorization!
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2025)

On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
di: Sahili, Ali Al, et al.
Pubblicazione: (2025)

Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
di: Naseh, Ali, et al.
Pubblicazione: (2025)

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
di: Xin, Rui, et al.
Pubblicazione: (2025)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
di: Ngong, Ivoline C., et al.
Pubblicazione: (2024)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
di: Wang, Tianchun, et al.
Pubblicazione: (2024)

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

Membership Inference Attacks and Privacy in Topic Modeling
di: Manzonelli, Nico, et al.
Pubblicazione: (2024)

Diffence: Fencing Membership Privacy With Diffusion Models
di: Peng, Yuefeng, et al.
Pubblicazione: (2023)

ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
di: Liu, Peihan, et al.
Pubblicazione: (2026)

Blind Baselines Beat Membership Inference Attacks for Foundation Models
di: Das, Debeshee, et al.
Pubblicazione: (2024)

R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
di: Naseh, Ali, et al.
Pubblicazione: (2025)

SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)
di: Meeus, Matthieu, et al.
Pubblicazione: (2024)

DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
di: Nguyen, Khanh, et al.
Pubblicazione: (2025)

Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models
di: Meeus, Matthieu, et al.
Pubblicazione: (2023)

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
di: Chang, Hongyan, et al.
Pubblicazione: (2024)

Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
di: Fu, Wenjie, et al.
Pubblicazione: (2023)

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

Differentially Private Knowledge Distillation via Synthetic Text Generation
di: Flemings, James, et al.
Pubblicazione: (2024)

GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detection
di: Rad, Melissa Kazemi, et al.
Pubblicazione: (2025)

Evaluations of Machine Learning Privacy Defenses are Misleading
di: Aerni, Michael, et al.
Pubblicazione: (2024)

Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
di: Mori, Junki, et al.
Pubblicazione: (2025)

The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
di: Meeus, Matthieu, et al.
Pubblicazione: (2025)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
di: Guo, Wenkai, et al.
Pubblicazione: (2025)

DP-MGTD: Privacy-Preserving Machine-Generated Text Detection via Adaptive Differentially Private Entity Sanitization
di: Wang, Lionel Z., et al.
Pubblicazione: (2026)

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
di: Rastogi, Saksham, et al.
Pubblicazione: (2025)

Can We Infer Confidential Properties of Training Data from LLMs?
di: Huang, Pengrun, et al.
Pubblicazione: (2025)

k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
di: Hou, Abe Bohan, et al.
Pubblicazione: (2024)

Membership Inference Attacks on LLM-based Recommender Systems
di: He, Jiajie, et al.
Pubblicazione: (2025)

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

On Reliability of Efficient Membership Inference Vulnerability Evaluation
di: Jälkö, Joonas, et al.
Pubblicazione: (2026)

Membership Inference over Diffusion-models-based Synthetic Tabular Data
di: Cheng, Peini, et al.
Pubblicazione: (2025)

STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio
di: Park, Seong-Gyu, et al.
Pubblicazione: (2026)

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text
di: Rao, Zixin, et al.
Pubblicazione: (2025)

FreqMark: Frequency-Based Watermark for Sentence-Level Detection of LLM-Generated Text
di: Xu, Zhenyu, et al.
Pubblicazione: (2024)

Detecting Pretraining Data from Large Language Models
di: Shi, Weijia, et al.
Pubblicazione: (2023)

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2023)

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
di: Naseh, Ali, et al.
Pubblicazione: (2025)

On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing
di: Liu, Zeyan, et al.
Pubblicazione: (2023)

Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
di: Krčo, Nataša, et al.
Pubblicazione: (2024)