mlsanityData to 7 Oct 2026

Exfiltration of personal information from ChatGPT via prompt injection

arXiv 2406.00199 ↗First posted 31 May 2024cs.CR cs.AI cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

We report that ChatGPT 4 and 4o are susceptible to a prompt injection attack that allows an attacker to exfiltrate users' personal data. It is applicable without the use of any 3rd party tools and all users are currently affected. This vulnerability is exacerbated by the recent introduction of ChatGPT's memory feature, which allows an attacker to command ChatGPT to monitor the user for the desired personal data.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 4 of its 10 references that are in the map. First posted on arXiv 31 May 2024.

Builds on

4 of 10 references.

References · 4

  1. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  2. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  3. 2023Prompt Injection attack against LLM-integrated Applicationscited by 568
  4. 2022Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examplescited by 65

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 1.

7 papers.

  1. 2025Design Patterns for Securing LLM Agents against Prompt Injectionscited by 67
  2. 2025Beyond Data Privacy: New Privacy Risks for Large Language Modelscited by 6
  3. 2025Toward a Safe Internet of Agentscited by 6
  4. 2025Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safetycited by 4
  5. 2025SAIF: A Comprehensive Framework for Evaluating the Risks of Generative AI in the Public Sectorcited by 2
  6. 2025LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systemscited by 1
  7. 2026An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environmentscited by 0