A First Look at Toxicity Injection Attacks on Open-domain Chatbots

Connor Weeks, Aravind Cheruvu, Sifat Muhammad Abdullah, Shravya Kanchi, Daphne Yao, Bimal Viswanath. A First Look at Toxicity Injection Attacks on Open-domain Chatbots. In Annual Computer Security Applications Conference, ACSAC 2023, Austin, TX, USA, December 4-8, 2023. pages 521-534, ACM, 2023. [doi]

Abstract

Abstract is missing.