arXiv AI June 4, 2026 By Jiachen Ma, Jiawen Zhang, Xiangtian Li, Bo Zou, Chaochao Lu, Chao Yang

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak

arXiv:2605. 20654v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation process.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

1d ago

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

arXiv AI

Aug 7

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.

By Yixin Tan, Zhe Yu, Rui Wen, Jun Sakuma

llms fine-tuning safety

arXiv AI

Jun 4

A Systematic Investigation of RL-Jailbreaking in LLMs

arXiv:2605. 07032v2 Announce Type: replace-cross Abstract: The evolution of generative models from next-token predictors to autonomous engines of complex systems necessitates rigorous safety hardening.

By Montaser Mohammedalamen, Kevin Roice, Reginald McLean, Alyssa Lefaivre \v{S}kopac

llms agents reinforcement-learning robotics safety

arXiv AI

Jun 11

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

arXiv:2602. 05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts.

By Xin Chen, Jie Zhang, Florian Tram\`er

llms agents reinforcement-learning fine-tuning safety

arXiv AI

Jul 20

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.

By Wenpeng Xing, Bohan Yang, Mohan Li, Chunqiang Hu, Haitao Xu, Ningyu Zhang, Bo Lin, Meng Han

llms multimodal benchmarks safety

arXiv AI

Jun 16

Automated jailbreak attack targeting multiple defense strategies

arXiv:2606. 16751v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks.

By Qi Wang, Chengcheng Wan, Weijia He, Yanqing Li, Hanqi Sun, Xiaodong Gu, Jiangtao Wang

llms multimodal safety

Related stories

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

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

A Systematic Investigation of RL-Jailbreaking in LLMs

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

Automated jailbreak attack targeting multiple defense strategies