# Persona Jailbreaking in Large Language Models

arXiv: https://arxiv.org/abs/2601.16466 · HTML: https://mlsanity.com/paper/2601.16466/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Contextualized Perturbation for Textual Adversarial Attack](https://mlsanity.com/paper/2009.07502/) (2020)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [Can LLM Agents Maintain a Persona in Discourse?](https://mlsanity.com/paper/2502.11843/) (2025)
- [Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning](https://mlsanity.com/paper/2310.10735/) (2023)
- [RealBehavior: A Framework for Faithfully Characterizing Foundation Models' Human-like Behavior Mechanisms](https://mlsanity.com/paper/2310.11227/) (2023)
- [CAPE: Context-Aware Personality Evaluation Framework for Large Language Models](https://mlsanity.com/paper/2508.20385/) (2025)

## Built on by (most cited first, 2 of 2)

- [What Models Express, Suppress, and Resist: Auditing Open-Weight LLMs with Persona Vectors](https://mlsanity.com/paper/2607.13162/) (2026)
- [Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning](https://mlsanity.com/paper/2608.11705/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed in domains such as education, mental health and customer support, where stable and consistent personas are critical for reliability. Yet, existing studies focus on narrative or role-playing tasks and overlook how adversarial conversational history alone can reshape induced personas. Black-box persona manipulation remains unexplored, raising concerns for robustness in realistic interactions. In response, we introduce the task of persona editing, which adversarially steers LLM traits through user-side inputs under a black-box, inference-only setting. To this end, we propose PHISH (Persona Hijacking via Implicit Steering in History), the first framework to expose a new vulnerability in LLM safety that embeds semantically loaded cues into user queries to gradually induce reverse personas. We also define a metric to quantify attack success. Across 3 benchmarks and 8 LLMs, PHISH predictably shifts personas, triggers collateral changes in correlated traits, and exhibits stronger effects in multi-turn settings. In high-risk domains mental health, tutoring, and customer support, PHISH reliably manipulates personas, validated by both human and LLM-as-Judge evaluations. Importantly, PHISH causes only a small reduction in reasoning benchmark performance, leaving overall utility largely intact while still enabling significant persona manipulation. While current guardrails offer partial protection, they remain brittle under sustained attack. Our findings expose new vulnerabilities in personas and highlight the need for context-resilient persona in LLMs. Our codebase and dataset is available at: https://github.com/Jivnesh/PHISH