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

arXiv: https://arxiv.org/abs/2505.09921 · HTML: https://mlsanity.com/paper/2505.09921/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily](https://mlsanity.com/paper/2311.08268/) (2023)
- [The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)](https://mlsanity.com/paper/2402.16893/) (2024)
- [Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2402.17840/) (2024)
- [Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses](https://mlsanity.com/paper/2406.01288/) (2024)
- [Reducing Privacy Risks in Online Self-Disclosures with Language Models](https://mlsanity.com/paper/2311.09538/) (2023)

## Built on by (most cited first, 11 of 11)

- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP](https://mlsanity.com/paper/2601.07395/) (2026)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy](https://mlsanity.com/paper/2510.04261/) (2025)
- [DP-Fusion: Token-Level Differentially Private Inference for Large Language Models](https://mlsanity.com/paper/2507.04531/) (2025)
- [Beyond Data Privacy: New Privacy Risks for Large Language Models](https://mlsanity.com/paper/2509.14278/) (2025)
- [Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode](https://mlsanity.com/paper/2602.00388/) (2026)
- [Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling](https://mlsanity.com/paper/2604.04842/) (2026)
- [Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models](https://mlsanity.com/paper/2603.27332/) (2026)
- [MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution](https://mlsanity.com/paper/2605.28646/) (2026)
- [STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs](https://mlsanity.com/paper/2608.08164/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment models can easily block. Meanwhile, Jailbreak attacks bypass LLM safety mechanisms to generate harmful content, but their role in privacy scenarios remains underexplored. In this paper, we examine the effectiveness of jailbreak attacks in extracting sensitive information, bridging privacy leakage and jailbreak attacks in LLMs. Moreover, we propose PIG, a novel framework targeting Personally Identifiable Information (PII) and addressing the limitations of current jailbreak methods. Specifically, PIG identifies PII entities and their types in privacy queries, uses in-context learning to build a privacy context, and iteratively updates it with three gradient-based strategies to elicit target PII. We evaluate PIG and existing jailbreak methods using two privacy-related datasets. Experiments on four white-box and two black-box LLMs show that PIG outperforms baseline methods and achieves state-of-the-art (SoTA) results. The results underscore significant privacy risks in LLMs, emphasizing the need for stronger safeguards. Our code is availble at https://github.com/redwyd/PrivacyJailbreak.