TaeBench: Improving Quality of Toxic Adversarial Examples NAACL

Jennifer Zhu | Dmitriy Bespalov | Liwen You | Ninad Kulkarni | Yanjun Qi |

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt. Generation for Enhanced LLM Content Moderation WOAH WS

Daniel Schwarz | Dmitriy Bespalov | Zhe Wang | Ninad Kulkarni | Yanjun Qi |

IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs EMNLP

Aosong Feng | Balasubramaniam Srinivasan | Yun Zhou | Zhichao Xu | Kang Zhou | Sheng Guan | Yueyan Chen | Xian Wu | Ninad Kulkarni | Yi Zhang | Zhengyuan Shen | Dmitriy Bespalov | Soumya Smruti Mishra | Yifei Teng | Darren Yow-Bang Wang | Haibo Ding | Lin Lee Cheong |

Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows EMNLP

Ninad Kulkarni | Xian Wu | Siddharth Varia | Dmitriy Bespalov |

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation EMNLP

Daniel Schwartz | Dmitriy Bespalov | Zhe Wang | Ninad Kulkarni | Yanjun Qi |