arXiv Machine Learning June 26, 2026 By Prarabdh Shukla, Ritik, Suhas Rao, Arpit Agarwal, Arjun Bhagoji

Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries

Read the original on arXiv Machine Learning →

arXiv:2606. 26936v1 Announce Type: cross Abstract: With a profusion of jailbreaks for LLMs now widely known, a growing concern is that non-expert malicious actors ("the average Jane") could elicit actionable responses to malicious requests.

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

arXiv AI

Jun 11

JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

arXiv:2606. 11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries.

By Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu

llms reinforcement-learning multimodal safety

arXiv AI

Jun 2

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

arXiv:2603. 24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations.

By Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko

llms agents multimodal benchmarks 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

Jun 19

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

arXiv:2606. 20470v1 Announce Type: cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents.

By Reza Soosahabi, Vivek Namsani

agents multimodal 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

Hugging Face Trending Papers

Jul 29

ToxScreen: Detecting Whether an LLM Has Been Poisoned

As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.

llms benchmarks

Related stories

JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems

VERA: Variational Inference Framework for Jailbreaking Large Language Models

ToxScreen: Detecting Whether an LLM Has Been Poisoned