| h4rm3l: A language for Composable Jailbreak Attack Synthesis | Aug 9, 2024 | BenchmarkingProgram Synthesis | —Unverified | 0 |
| "Haet Bhasha aur Diskrimineshun": Phonetic Perturbations in Code-Mixed Hinglish to Red-Team LLMs | May 20, 2025 | Image GenerationRed Teaming | —Unverified | 0 |
| Finding Safety Neurons in Large Language Models | Jun 20, 2024 | MisinformationRed Teaming | —Unverified | 0 |
| A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI | Apr 23, 2024 | Prompt EngineeringRed Teaming | —Unverified | 0 |
| Fast Proxies for LLM Robustness Evaluation | Feb 14, 2025 | Red Teaming | —Unverified | 0 |
| HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback | Mar 13, 2024 | Language ModellingLarge Language Model | —Unverified | 0 |
| Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation | May 24, 2025 | Intent DetectionNatural Language Understanding | —Unverified | 0 |
| Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming | Feb 22, 2025 | DiversityIn-Context Learning | —Unverified | 0 |
| A Framework for Evaluating Emerging Cyberattack Capabilities of AI | Mar 14, 2025 | Red Teaming | —Unverified | 0 |
| Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts | Nov 15, 2023 | Adversarial AttackRed Teaming | —Unverified | 0 |
