arXiv Machine Learning July 7, 2026 By Shai Feldman, Yaniv Romano

How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation

Read the original on arXiv Machine Learning →

arXiv:2605. 06605v2 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.

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 Machine Learning.

arXiv AI

Jun 9

PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits

arXiv:2510. 17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate.

By Neeladri Bhuiya, Madhav Aggarwal, Diptanshu Purwar

llms agents multimodal 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 Machine Learning

Jun 9

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.

By Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut

llms agents 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

4d ago

Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

arXiv:2609.36849v1 Announce Type: cross Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...

By Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang

llms safety

arXiv AI

Aug 6

Dynamic Jailbreaking Attack

arXiv:2510. 02422v4 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy.

By Kedong Xiu, Yunhan Yang, Churui Zeng, Tianhang Zheng, Xinzhe Huang, Di Wang, Puning Zhao, Zhan Qin, Kui Ren

llms multimodal safety

One email a morning, machine-written

Related stories

PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits

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

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

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

Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

Dynamic Jailbreaking Attack