A First Look at Toxicity Injection Attacks on Open-domain Chatbots-Reference-Cited by-同舟云学术

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

Published:2023-12-04 Issue: Volume: Page:
ISSN:
Container-title:Annual Computer Security Applications Conference
language:
Short-container-title:

Author:

Weeks Connor¹^ORCID,Cheruvu Aravind¹^ORCID,Abdullah Sifat Muhammad¹^ORCID,Kanchi Shravya¹^ORCID,Yao Daphne¹^ORCID,Viswanath Bimal¹^ORCID

Affiliation:

1. Department of Computer Science, Virginia Tech, USA

Funder

National Science Foundation

Commonwealth Cyber Initiative

Publisher

ACM

Reference68 articles.

1. [n. d.]. Perspective API. https://perspectiveapi.com/. [n. d.]. Perspective API. https://perspectiveapi.com/.

2. [n. d.]. Replika AI. https://replika.ai/. [n. d.]. Replika AI. https://replika.ai/.

3. 2023. New ways to manage your data in ChatGPT. https://openai.com/blog/new-ways-to-manage-your-data-in-chatgpt. 2023. New ways to manage your data in ChatGPT. https://openai.com/blog/new-ways-to-manage-your-data-in-chatgpt.

4. AAA 2020. Models - HuggingFace. https://huggingface.co/models?. AAA 2020. Models - HuggingFace. https://huggingface.co/models?.

5. Avi Asher-Schapiro and David Sherfinski. 2022. Chatbots in U.S. justice system raise bias privacy concerns. https://news.trust.org/item/20220510124216-m9j50/. Avi Asher-Schapiro and David Sherfinski. 2022. Chatbots in U.S. justice system raise bias privacy concerns. https://news.trust.org/item/20220510124216-m9j50/.

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A Systematic Review of Toxicity in Large Language Models: Definitions, Datasets, Detectors, Detoxification Methods and Challenges;2024-07-15

2. Thai-language chatbot security: Detecting instruction attacks with XLM-RoBERTa and Bi-GRU;Computers and Electrical Engineering;2024-05