paper-with-me

Papers

Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation

2025-12-20 · Zehao Liu, Xi Lin arxiv

Large Language Models (LLMs) have gained considerable popularity and protected by increasingly sophisticated safety mechanisms. However, jailbreak attacks continue to pose a critical security threat by inducing models to generate policy-violating behaviors. Current paradigms focus on input-level anomalies, overlooking that the model's internal psychometric state can be systematically manipulated. To address this, we introduce Psychological Jailbreak, a new jailbreak attack paradigm that exposes a stateful psychological attack surface in LLMs, where attackers exploit the manipulation of a model's psychological state across interactions. Building on this insight, we propose Human-like Psychological Manipulation (HPM), a black-box jailbreak method that dynamically profiles a target model's latent psychological vulnerabilities and synthesizes tailored multi-turn attack strategies. By leveraging the model's optimization for anthropomorphic consistency, HPM creates a psychological pressure where social compliance overrides safety constraints. To systematically measure psychological safety, we construct an evaluation framework incorporating psychometric datasets and the Policy Corruption Score (PCS). Benchmarking against various models (e.g., GPT-4o, DeepSeek-V3, Gemini-2-Flash), HPM achieves a mean Attack Success Rate (ASR) of 88.1%, outperforming state-of-the-art attack baselines. Our experiments demonstrate robust penetration against advanced defenses, including adversarial prompt optimization (e.g., RPO) and cognitive interventions (e.g., Self-Reminder). Ultimately, PCS analysis confirms HPM induces safety breakdown to satisfy manipulated contexts. Our work advocates for a fundamental paradigm shift from static content filtering to psychological safety, prioritizing the development of psychological defense mechanisms against deep cognitive manipulation.

📄 PDF Abstract BibTeX arXiv:2512.18244

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Jailbreaking Large Vision Language Models in Intelligent Transportation Systems

2025-11-17 · Badhan Chandra Das, Md Tasnim Jawad, Md Jueal Mia, M. Hadi Amini 외 arxiv

Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attac…

Visual Question AnsweringMultimodal Reasoning

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…

Automatic Jailbreaking of the Text-to-Image Generative AI Systems

2024-05-26 · Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang 외

Recent AI systems have shown extremely powerful performance, even surpassing human performance, on various tasks such as information retrieval, language generation, and image generation based on large language models (LL…

Image GenerationInformation RetrievalMachine UnlearningText Generation

How to Trick Your AI TA: A Systematic Study of Academic Jailbreaking in LLM Code Evaluation

2025-12-11 · Devanshu Sahoo, Vasudev Majhi, Arjun Neekhra, Yash Sinha 외 arxiv

The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial…

Many-Turn Jailbreaking

2025-08-09 · Xianjun Yang, Liqiang Xiao, Shiyang Li, Faisal Ladhak 외 arxiv

Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one specific query. On the contrary, the advanced…