The Dangerous Effects of a Frustratingly Easy LLMs Jailbreak Attack by Marco Bombieri, Simone Paolo Ponzetto, Marco Rospocher

Subjects: Get full text

JailbreakTracer: Explainable Detection of Jailbreaking Prompts in LLMs Using Synthetic Data Generation by Md. Faiyaz Abdullah Sayeedi, Maaz Bin Hossain, Md. Kamrul Hassan, Sabrina Afrin, Molla Md. Sabit Hossain, Md. Shohrab Hossain

Subjects: Get full text

LLM Abuse Prevention Tool Using GCG Jailbreak Attack Detection and DistilBERT-Based Ethics Judgment by Qiuyu Chen, Shingo Yamaguchi, Yudai Yamamoto

Subjects: Get full text

Improving LLM Outputs Against Jailbreak Attacks With Expert Model Integration by Tatia Tsmindashvili, Ana Kolkhidashvili, Dachi Kurtskhalia, Nino Maghlakelidze, Elene Mekvabishvili, Guram Dentoshvili, Orkhan Shamilov, Zaal Gachechiladze, Steven Saporta, David Dachi Choladze

Subjects: Get full text

Quantization-Based Jailbreaking Vulnerability Analysis: A Study on Performance and Safety of the Llama3-8B-Instruct Model by Jaesik Lee

Subjects: Get full text