mlsanityData to 14 Oct 2026

Exploring the Privacy Protection Capabilities of Chinese Large Language Models

arXiv 2403.18205 ↗First posted 27 Mar 2024cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs), renowned for their impressive capabilities in various tasks, have significantly advanced artificial intelligence. Yet, these advancements have raised growing concerns about privacy and security implications. To address these issues and explain the risks inherent in these models, we have devised a three-tiered progressive framework tailored for evaluating privacy in language systems. This framework consists of progressively complex and in-depth privacy test tasks at each tier. Our primary objective is to comprehensively evaluate the sensitivity of large language models to private information, examining how effectively they discern, manage, and safeguard sensitive data in diverse scenarios. This systematic evaluation helps us understand the degree to which these models comply with privacy protection guidelines and the effectiveness of their inherent safeguards against privacy breaches. Our observations indicate that existing Chinese large language models universally show privacy protection shortcomings. It seems that at the moment this widespread issue is unavoidable and may pose corresponding privacy risks in applications based on these models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 27 Mar 2024.

Builds on

35 of 49 references.

References · 35

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  8. 2020Extracting Training Data from Large Language Modelscited by 2,189
  9. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  11. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  12. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
23 more
  1. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  2. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
  3. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 625
  4. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  5. 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 548
  6. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  7. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 489
  8. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 393
  9. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  10. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
  11. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easilycited by 259
  12. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 200
  13. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Modelscited by 175
  14. 2021Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?cited by 93
  15. 2023Safety Assessment of Chinese Large Language Modelscited by 85
  16. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 70
  17. 2023Privacy Issues in Large Language Models: A Surveycited by 60
  18. 2023Assessing Prompt Injection Risks in 200+ Custom GPTscited by 55
  19. 2023Identifying and Mitigating Vulnerabilities in LLM-Integrated Applicationscited by 54
  20. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 51
  21. 2023Demystifying RCE Vulnerabilities in LLM-Integrated Appscited by 37
  22. 2023Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimationcited by 36
  23. 2023Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakagecited by 28

Built on by

Not cited yet.