arXiv AI September 3, 2026 By Siyu Chen, Haoran Wang, Xiaojian Li, Yao Huang, Yinpeng Dong, Wei Xu

Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking

The paper introduces BLUEPRINT, a safety‑evaluation framework that separates a factorized social‑influence strategy space from WORLDVIEWSIM, a cross‑turn situational context module. Using Monte Carlo Tree Search, it optimizes turn‑level combinations of 18 theory‑grounded influence factors across a four‑turn trajectory, achieving near‑ceiling ASR on six frontier models with an average of only 2.46 queries. The study reveals that model‑specific vulnerabilities arise from distinct influence factors and strategy transitions, yet all models share a recovery pathway that shifts toward concrete, executable task framing to escape hard‑refusal states, highlighting the importance of monitoring how dialogue state makes unsafe requests appear actionable.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 11

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).

By Adarsh Kumarappan, Ananya Mujoo

llms robotics multimodal benchmarks safety

arXiv AI

Jul 2

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).

By Junlong Liu, Haobo Wang, Weiqi Luo, Xiaojun Jia

llms benchmarks safety

arXiv AI

Jun 2

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models

arXiv:2606. 01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination.

By Zhiqing Ma, Zhonghao Xu, Dong Yu, Chen Kang, Changliang Li, Pengyuan Liu

llms agents multimodal benchmarks safety

arXiv AI

Jul 28

Do LLMs Know Their Vulnerable Scenarios?

arXiv:2607. 23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards.

By Ziheng Peng, Huiqi Deng, Haoran Jing, Xuankun Rong, Jiahui Han, Xiting Wang, Na Zou, Xia Hu

llms rag benchmarks safety

arXiv AI

Aug 10

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.

By Shubham Kumar, Narendra Ahuja

llms benchmarks safety

arXiv AI

Aug 18

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.

By Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu, Ruihong Huang

llms robotics fine-tuning multimodal benchmarks safety

One email a morning, machine-written

Related stories

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models

Do LLMs Know Their Vulnerable Scenarios?

Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation