Saved in:
Bibliographic Details
Main Authors: Barrett, Clark, Boyd, Brad, Burzstein, Elie, Carlini, Nicholas, Chen, Brad, Choi, Jihye, Chowdhury, Amrita Roy, Christodorescu, Mihai, Datta, Anupam, Feizi, Soheil, Fisher, Kathleen, Hashimoto, Tatsunori, Hendrycks, Dan, Jha, Somesh, Kang, Daniel, Kerschbaum, Florian, Mitchell, Eric, Mitchell, John, Ramzan, Zulfikar, Shams, Khawaja, Song, Dawn, Taly, Ankur, Yang, Diyi
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.14840
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929194788716544
author Barrett, Clark
Boyd, Brad
Burzstein, Elie
Carlini, Nicholas
Chen, Brad
Choi, Jihye
Chowdhury, Amrita Roy
Christodorescu, Mihai
Datta, Anupam
Feizi, Soheil
Fisher, Kathleen
Hashimoto, Tatsunori
Hendrycks, Dan
Jha, Somesh
Kang, Daniel
Kerschbaum, Florian
Mitchell, Eric
Mitchell, John
Ramzan, Zulfikar
Shams, Khawaja
Song, Dawn
Taly, Ankur
Yang, Diyi
author_facet Barrett, Clark
Boyd, Brad
Burzstein, Elie
Carlini, Nicholas
Chen, Brad
Choi, Jihye
Chowdhury, Amrita Roy
Christodorescu, Mihai
Datta, Anupam
Feizi, Soheil
Fisher, Kathleen
Hashimoto, Tatsunori
Hendrycks, Dan
Jha, Somesh
Kang, Daniel
Kerschbaum, Florian
Mitchell, Eric
Mitchell, John
Ramzan, Zulfikar
Shams, Khawaja
Song, Dawn
Taly, Ankur
Yang, Diyi
contents Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and diffusion models, have shown remarkable capabilities (e.g., in-context learning, code-completion, and text-to-image generation and editing). However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks. This paper reports the findings of a workshop held at Google (co-organized by Stanford University and the University of Wisconsin-Madison) on the dual-use dilemma posed by GenAI. This paper is not meant to be comprehensive, but is rather an attempt to synthesize some of the interesting findings from the workshop. We discuss short-term and long-term goals for the community on this topic. We hope this paper provides both a launching point for a discussion on this important topic as well as interesting problems that the research community can work to address.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14840
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Identifying and Mitigating the Security Risks of Generative AI
Barrett, Clark
Boyd, Brad
Burzstein, Elie
Carlini, Nicholas
Chen, Brad
Choi, Jihye
Chowdhury, Amrita Roy
Christodorescu, Mihai
Datta, Anupam
Feizi, Soheil
Fisher, Kathleen
Hashimoto, Tatsunori
Hendrycks, Dan
Jha, Somesh
Kang, Daniel
Kerschbaum, Florian
Mitchell, Eric
Mitchell, John
Ramzan, Zulfikar
Shams, Khawaja
Song, Dawn
Taly, Ankur
Yang, Diyi
Artificial Intelligence
Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and diffusion models, have shown remarkable capabilities (e.g., in-context learning, code-completion, and text-to-image generation and editing). However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks. This paper reports the findings of a workshop held at Google (co-organized by Stanford University and the University of Wisconsin-Madison) on the dual-use dilemma posed by GenAI. This paper is not meant to be comprehensive, but is rather an attempt to synthesize some of the interesting findings from the workshop. We discuss short-term and long-term goals for the community on this topic. We hope this paper provides both a launching point for a discussion on this important topic as well as interesting problems that the research community can work to address.
title Identifying and Mitigating the Security Risks of Generative AI
topic Artificial Intelligence
url https://arxiv.org/abs/2308.14840