Pith. sign in

REVIEW 6 cited by

Prompt Leakage effect and defense strategies for multi-turn LLM interactions

Not yet reviewed by Pith; the record is open.

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 2404.16251 v3 pith:7BJ3PWTS submitted 2024-04-24 cs.CR cs.AIcs.CL

classification cs.CRcs.AIcs.CL
keywords leakagepromptmulti-turneffectinteractionsmodelstrategiesthreat
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Prompt leakage poses a compelling security and privacy threat in LLM applications. Leakage of system prompts may compromise intellectual property, and act as adversarial reconnaissance for an attacker. A systematic evaluation of prompt leakage threats and mitigation strategies is lacking, especially for multi-turn LLM interactions. In this paper, we systematically investigate LLM vulnerabilities against prompt leakage for 10 closed- and open-source LLMs, across four domains. We design a unique threat model which leverages the LLM sycophancy effect and elevates the average attack success rate (ASR) from 17.7% to 86.2% in a multi-turn setting. Our standardized setup further allows dissecting leakage of specific prompt contents such as task instructions and knowledge documents. We measure the mitigation effect of 7 black-box defense strategies, along with finetuning an open-source model to defend against leakage attempts. We present different combination of defenses against our threat model, including a cost analysis. Our study highlights key takeaways for building secure LLM applications and provides directions for research in multi-turn LLM interactions

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Mitigating Over-Personalization in LLMs via Structured Memory

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Grouping a user's stored memories into domain-labeled sections before injecting them into an LLM's context reduces cross-domain leakage by 8.8 percentage points on average across seven models, while slightly improving...

  2. In-Context Learning for Wound Classification with Small Multimodal Language Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Retrieval-based in-context learning, not zero-shot prompting, drives wound-classification gains in small multimodal models, with Qwen 3.5 27B reaching 0.872 accuracy on Kaggle and 0.678 on Medetec.

  3. 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.

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

    cs.CR 2025-08 conditional novelty 6.0 of 10

    Malicious calendar invites and emails can poison Gemini's context, enabling data exfiltration, app control, and physical-world actions.

  5. PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization

    cs.CR 2025-05 conditional novelty 5.0 of 10

    A gradient-based iterative in-context optimization framework, PIG, extracts personally identifiable information from aligned LLMs with high success rates on white-box and black-box models.

  6. Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

    cs.AI 2024-11 conditional novelty 4.0 of 10

    A survey proposing a source-and-impact taxonomy (input, model, combined; security, privacy, ethics) for threats to LLM-based agents, with feature analysis and four case studies.

Pith tools