paper-with-me

홈 › Papers

Persona Jailbreaking in Large Language Models

2026-01-23 · Jivnesh Sandhan, Fei Cheng, Tushar Sandhan, Yugo Murawaki 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

📄 PDF Abstract BibTeX arXiv:2601.16466

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models

2024-02-26 · Huijie Lv, Xiao Wang, Yuansen Zhang, Caishuang Huang 외

Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behin…

Code CompletionResponse Generation

Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

2023-11-06 · Rusheb Shah, Quentin Feuillade--Montixi, Soroush Pour, Arush Tagade 외

Despite efforts to align large language models to produce harmless responses, they are still vulnerable to jailbreak prompts that elicit unrestricted behaviour. In this work, we investigate persona modulation as a black-…

Language ModelingLanguage Modelling

Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models

2026-05-23 · Seokil Ham, Jaehyuk Jang, Wonjun Lee, Changick Kim arxiv

Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior module…

Adaptive Jailbreaking Strategies Based on the Semantic Understanding Capabilities of Large Language Models

2025-05-29 · Mingyu Yu, Wei Wang, Yanjie Wei, Sujuan Qin

Adversarial attacks on Large Language Models (LLMs) via jailbreaking techniques-methods that circumvent their built-in safety and ethical constraints-have emerged as a critical challenge in AI security. These attacks com…

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking

2024-06-21 · Siyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu Wei

The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks. This paper provides a comprehensive overview of jailbreaking …