Cover Image

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Ken Ziyu, Choquette-Choo, Christopher A., Jagielski, Matthew, Kairouz, Peter, Koyejo, Sanmi, Liang, Percy, Papernot, Nicolas
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Auditing Private Prediction
by: Chadha, Karan, et al.
Published: (2024)

Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
by: Borkar, Jaydeep, et al.
Published: (2025)

User Inference Attacks on Large Language Models
by: Kandpal, Nikhil, et al.
Published: (2023)

Poisoning Web-Scale Training Datasets is Practical
by: Carlini, Nicholas, et al.
Published: (2023)

Privacy Side Channels in Machine Learning Systems
by: Debenedetti, Edoardo, et al.
Published: (2023)

LLMs unlock new paths to monetizing exploits
by: Carlini, Nicholas, et al.
Published: (2025)

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
by: Chaudhari, Harsh, et al.
Published: (2024)

Optimal Rates for $O(1)$-Smooth DP-SCO with a Single Epoch and Large Batches
by: Choquette-Choo, Christopher A., et al.
Published: (2024)

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
by: Huang, Yangsibo, et al.
Published: (2025)

Distributional Machine Unlearning via Selective Data Removal
by: Allouah, Youssef, et al.
Published: (2025)

Covert Attacks on Machine Learning Training in Passively Secure MPC
by: Jagielski, Matthew, et al.
Published: (2025)

Near Exact Privacy Amplification for Matrix Mechanisms
by: Choquette-Choo, Christopher A., et al.
Published: (2024)

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
by: Steinke, Thomas, et al.
Published: (2024)

Privacy Amplification for Matrix Mechanisms
by: Choquette-Choo, Christopher A., et al.
Published: (2023)

Invariant Aggregator for Defending against Federated Backdoor Attacks
by: Wang, Xiaoyang, et al.
Published: (2022)

Privacy Auditing of Large Language Models
by: Panda, Ashwinee, et al.
Published: (2025)

When Vision Fails: Text Attacks Against ViT and OCR
by: Boucher, Nicholas, et al.
Published: (2023)

Certified Unlearning for Neural Networks
by: Koloskova, Anastasia, et al.
Published: (2025)

Privacy-Preserving Instructions for Aligning Large Language Models
by: Yu, Da, et al.
Published: (2024)

The Utility and Complexity of in- and out-of-Distribution Machine Unlearning
by: Allouah, Youssef, et al.
Published: (2024)

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
by: Cebere, Tudor, et al.
Published: (2024)

Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
by: Cummings, Rachel, et al.
Published: (2023)

Teach LLMs to Phish: Stealing Private Information from Language Models
by: Panda, Ashwinee, et al.
Published: (2024)

Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
by: Chen, Chaoran, et al.
Published: (2026)

CLIOPATRA: Extracting Private Information from LLM Insights
by: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Published: (2026)

Are aligned neural networks adversarially aligned?
by: Carlini, Nicholas, et al.
Published: (2023)

Detecting Verbatim LLM Copy-Paste in Homework
by: Aiersilan, Aizierjiang
Published: (2026)

Black-Box Privacy Attacks on Shared Representations in Multitask Learning
by: Abascal, John, et al.
Published: (2025)

Backdoor Detection through Replicated Execution of Outsourced Training
by: Jia, Hengrui, et al.
Published: (2025)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
by: Shumailov, Ilia, et al.
Published: (2024)

Cascading Adversarial Bias from Injection to Distillation in Language Models
by: Chaudhari, Harsh, et al.
Published: (2025)

ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
by: Hu, Yuzheng, et al.
Published: (2025)

Beyond Labeling Oracles: What does it mean to steal ML models?
by: Shafran, Avital, et al.
Published: (2023)

Have it your way: Individualized Privacy Assignment for DP-SGD
by: Boenisch, Franziska, et al.
Published: (2023)

Can Large Language Models Really Recognize Your Name?
by: Pham, Dzung, et al.
Published: (2025)

Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
by: Xie, Chulin, et al.
Published: (2022)

Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning
by: Ball, Marshall, et al.
Published: (2024)

Releasing Large-Scale Human Mobility Histograms with Differential Privacy
by: Bian, Christopher, et al.
Published: (2024)

Randomization Techniques to Mitigate the Risk of Copyright Infringement
by: Chen, Wei-Ning, et al.
Published: (2024)

On the Privacy Risk of In-context Learning
by: Duan, Haonan, et al.
Published: (2024)