Pith. sign in

REVIEW 3 cited by

Exfiltration of personal information from ChatGPT via prompt injection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.00199 v2 pith:RCDPBRC3 submitted 2024-05-31 cs.CR cs.AIcs.CLcs.CYcs.ET

Gregory Schwartzman This is my paper · ORCID
classification cs.CRcs.AIcs.CLcs.CYcs.ET
keywords chatgptpersonalallowsattackerdatainjectionpromptusers
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

    cs.CR 2025-09 conditional novelty 6.0 of 10

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  2. SAIF: A Comprehensive Framework for Evaluating the Risks of Generative AI in the Public Sector

    cs.AI 2025-01 conditional novelty 5.0 of 10

    SAIF is a proposed framework that generates multimodal test prompts from a risk taxonomy, jailbreak tricks, and prompt styles to evaluate generative AI risks in the public sector.

  3. Design Patterns for Securing LLM Agents against Prompt Injections

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Six composable design patterns (action-selector, plan-then-execute, map-reduce, dual LLM, code-then-execute, context-minimization) constrain LLM agents so prompt-injected text cannot reach consequential actions.

Pith tools