arXiv Machine Learning August 28, 2026 By Yu Zhe, Yixin Tan, Junhao Wei, Wang Chen

A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families

Read the original on arXiv Machine Learning →

The paper investigates safety risks in model merging, showing that even when all constituent models are individually safety‑aligned, merging can expose a jailbreak vulnerability rooted in the pretrained foundation model. It introduces Basin‑Aware Jailbreak (BAJ), a min–max optimization method that generates adversarial suffixes transferable across merged models sharing the same backbone, without needing the exact merging coefficients or checkpoints. Experiments demonstrate BAJ’s high transfer success rates across diverse backbones and merging settings, and its resilience against existing defenses.

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

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

Aug 20

Jailbreaking in the Haystack

The paper "Jailbreaking in the Haystack" introduces NINJA, a jailbreak technique that exploits long-context language models by appending benign, model-generated content to harmful user goals. It demonstrates that the position of harmful goals within the context is crucial for safety, and shows that NINJA significantly boosts attack success rates on models such as LLaMA, Qwen, Mistral, and Gemini. Unlike previous methods, NINJA is low-resource, transferable, less detectable, and compute‑optimal, revealing that carefully crafted benign long contexts can expose fundamental vulnerabilities in modern LMs.

By Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena, Ziqian Zhong, Alexander Robey, Aditi Raghunathan

llms agents benchmarks safety

arXiv Machine Learning

Jun 2

VERA: Variational Inference Framework for Jailbreaking Large Language Models

arXiv:2506. 22666v3 Announce Type: replace-cross Abstract: The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings.

By Anamika Lochab, Lu Yan, Patrick Pynadath, Xiangyu Zhang, Ruqi Zhang

llms benchmarks safety

arXiv Machine Learning

Jun 16

Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

arXiv:2606. 16242v1 Announce Type: new Abstract: The Rapid Response (RR) framework, deployed in production systems, including Anthropic's ASL-3 safeguards, continuously improves jailbreak-detection classifiers.

By David Huang, Jaewon Chang, Avidan Shah, Prateek Mittal, Chawin Sitawarin

safety

arXiv Machine Learning

Jun 30

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.

By Yannick Assogba, Jacopo Cortellazzi, Javier Abad, Pau Rodriguez, Xavier Suau, Arno Blaas

llms diffusion safety

arXiv AI

Jul 23

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

arXiv:2607. 19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates.

By Qingjia Huang, Jingyu Zhang, Jianguo Wu, Yakai Li, Weijuan Zhang, Yankai Rong, Junyi Yao, Shengzhi Zhang, Xiaoqi Jia

llms benchmarks safety

One email a morning, machine-written

Related stories

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

Jailbreaking in the Haystack

VERA: Variational Inference Framework for Jailbreaking Large Language Models

Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models