Scalable Extraction of Training Data from (Production) Language Models

28 November 2023

Christopher A. Choquette-Choo

ArXiv (abs)PDF HTML HuggingFace (3 upvotes)

Papers citing "Scalable Extraction of Training Data from (Production) Language Models"

50 / 281 papers shown

Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMs

Kunj Joshi

David A. Smith

02 Dec 2025

Quantifying the Privacy Implications of High-Fidelity Synthetic Network Traffic

523

25 Nov 2025

For Those Who May Find Themselves on the Red Team

Tyler Shoemaker

23 Nov 2025

Leak@

k

: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding

352

07 Nov 2025

Remembering Unequally: Global and Disciplinary Bias in LLM-Generated Co-Authorship Networks

Ghazal Kalhor

Afra Mashhadi

01 Nov 2025

RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline

127

29 Oct 2025

PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning

132

27 Oct 2025

Leverage Unlearning to Sanitize LLMs

Antoine Boutet

Lucas Magnana

MU MedIm

193

24 Oct 2025

CircuitGuard: Mitigating LLM Memorization in RTL Code Generation Against IP Leakage

122

22 Oct 2025

Extracting alignment data in open models

Federico Barbero

Xiangming Gu

Christopher A. Choquette-Choo

183

21 Oct 2025

An Investigation of Memorization Risk in Healthcare Foundation Models

114

14 Oct 2025

The Model's Language Matters: A Comparative Privacy Analysis of LLMs

270

09 Oct 2025

On the Theory of Continual Learning with Gradient Descent for Neural Networks

151

07 Oct 2025

Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique

Lorena Gonzalez-Manzano

WaLM

213

07 Oct 2025

External Data Extraction Attacks against Retrieval-Augmented Large Language Models

275

03 Oct 2025

$UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models$

UpSafe

^\circ

C: Upcycling for Controllable Safety in Large Language Models

02 Oct 2025

Adaptive Token-Weighted Differential Privacy for LLMs: Not All Tokens Require Equal Protection

136

27 Sep 2025

Federated Learning of Quantile Inference under Local Differential Privacy

108

26 Sep 2025

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks

305

25 Sep 2025

GEP: A GCG-Based method for extracting personally identifiable information from chatbots built on small language models

Jieli Zhu

Vi Ngoc-Nha Tran

226

25 Sep 2025

Enterprise AI Must Enforce Participant-Aware Access Control

Shashank Shreedhar Bhatt

Tanmay Rajore

Khushboo Aggarwal

Ganesh Ananthanarayanan

...

218

18 Sep 2025

AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and PropositionsKnowledge-Based Systems (KBS), 2025

...

171

14 Sep 2025

A Biosecurity Agent for Lifecycle LLM Biosecurity Alignment

Meiyin Meng

Zaixi Zhang

LLMAG

165

13 Sep 2025

Why Data Anonymization Has Not Taken OffCustomer Needs and Solutions (CNS), 2025

Matthew J. Schneider

James Bailie

Dawn Iacobucci

191

12 Sep 2025

User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies

132

05 Sep 2025

Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs

192

02 Sep 2025

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation

31 Aug 2025

Embodied AI: Emerging Risks and Opportunities for Policy Action

290

28 Aug 2025

Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models

Qiming Guo

Jinwen Tang

Xingran Huang

156

25 Aug 2025

On the Edge of Memorization in Diffusion Models

276

25 Aug 2025

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation

...

161

21 Aug 2025

A Study of Privacy-preserving Language Modeling Approaches

Pritilata Saha

Abhirup Sinha

PILM

236

21 Aug 2025

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous

Ben Nassi

Stav Cohen

Or Yair

127

16 Aug 2025

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

186

14 Aug 2025

The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

Abhilasha Ravichander

Sahana Ramnath

Yejin Choi

Sai Praneeth Karimireddy

Niloofar Mireshghallah

Xiang Ren

AAML MLAU

304

13 Aug 2025

PETLP: A Privacy-by-Design Pipeline for Social Media Data in AI Research

177

12 Aug 2025

Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models

Badrinath Ramakrishnan

Akshaya Balaji

MU PILM

283

10 Aug 2025

Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy

199

06 Aug 2025

Current State in Privacy-Preserving Text Preprocessing for Domain-Agnostic NLP

100

05 Aug 2025

Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs

Jérémie Dentan

Davide Buscaldi

Sonia Vanier

191

04 Aug 2025

Bridging AI Innovation and Healthcare Needs: Lessons Learned from Incorporating Modern NLP at The BC Cancer Registry

129

27 Jul 2025

Differentiating hype from practical applications of large language models in medicine - a primer for healthcare professionals

Elisha D.O. Roberson

LM&MA

25 Jul 2025

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training

Pengfei Du

AAML

148

14 Jul 2025

Memorization Sinks: Isolating Memorization during LLM Training

Gaurav R. Ghosal

Pratyush Maini

Aditi Raghunathan

240

14 Jul 2025

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage

249

03 Jul 2025

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy

152

30 Jun 2025

A Common Pool of Privacy Problems: Legal and Technical Lessons from a Large-Scale Web-Scraped Machine Learning Dataset

350

20 Jun 2025

Approximating Language Model Training Data from Weights

260

18 Jun 2025

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and MitigationACM Asia Conference on Computer and Communications Security (AsiaCCS), 2025

Yashothara Shanmugarasa

Ming Ding

M. Chamikara

Thierry Rakotoarivelo

PILM AILaw

436

15 Jun 2025

Memorization in Language Models through the Lens of Intrinsic Dimension

Stefan Arnold

PILM

321

11 Jun 2025