# PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage

arXiv: https://arxiv.org/abs/2507.02332 · HTML: https://mlsanity.com/paper/2507.02332/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 39 of its 46 references that are in the map.
- First posted on arXiv 3 Jul 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 39)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (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)
- [A StrongREJECT for Empty Jailbreaks](https://mlsanity.com/paper/2402.10260/) (2024)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [JudgeBench: A Benchmark for Evaluating LLM-based Judges](https://mlsanity.com/paper/2410.12784/) (2024)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs](https://mlsanity.com/paper/2410.05295/) (2024)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [Understanding Reasoning in Thinking Language Models via Steering Vectors](https://mlsanity.com/paper/2506.18167/) (2025)
- [SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering](https://mlsanity.com/paper/2408.11491/) (2024)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [Automated Red Teaming with GOAT: the Generative Offensive Agent Tester](https://mlsanity.com/paper/2410.01606/) (2024)

## Built on by (most cited first, 5 of 5)

- [Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models](https://mlsanity.com/paper/2603.05773/) (2026)
- [LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning](https://mlsanity.com/paper/2607.02513/) (2026)
- [ShallowJail: Steering Jailbreaks against Large Language Models](https://mlsanity.com/paper/2602.07107/) (2026)
- [GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints](https://mlsanity.com/paper/2601.16905/) (2026)
- [Clinically Grounded Privacy Evaluation of Medical LMs](https://mlsanity.com/paper/2606.09590/) (2026)

## Abstract (arXiv)

This paper investigates privacy jailbreaking in LLMs via steering, focusing on whether manipulating activations can bypass LLM alignment and alter response behaviors to privacy related queries (e.g., a certain public figure's sexual orientation). We begin by identifying attention heads predictive of refusal behavior for private attributes (e.g., sexual orientation) using lightweight linear probes trained with privacy evaluator labels. Next, we steer the activations of a small subset of these attention heads guided by the trained probes to induce the model to generate non-refusal responses. Our experiments show that these steered responses often disclose sensitive attribute details, along with other private information about data subjects such as life events, relationships, and personal histories that the models would typically refuse to produce. Evaluations across four LLMs reveal jailbreaking disclosure rates of at least 95%, with more than 50% on average of these responses revealing true personal information. Our controlled study demonstrates that private information memorized in LLMs can be extracted through targeted manipulation of internal activations.