1 option
Mitigating Prompt Injection and Prompt Hacking / with Ray Villalobos
- Format:
- Video
- Author/Creator:
- Villalobos, Ray, speaker.
- Language:
- English
- Genre:
- Instructional films.
- Educational films.
- Physical Description:
- 1 online resource
- Place of Publication:
- Carpenteria, CA : linkedin.com, 2023.
- System Details:
- digital
- Summary:
- Understand and learn to mitigate the issues and problems with prompt hacking, a technique used by malicious hackers to manipulate large language models.
- As large language models like Chat GPT, Bard, Claude and others have penetrated the culture, hackers are busy attempting to manipulate the models they are based on like GPT, Palm2 and others in order to change how they respond. In this course, Ray Villalobos discusses the mechanisms behind prompt hacking and some of the mitigation techniques. In a world where companies are rushing to develop their own implementations of these popular models, it's important to understand the concepts behind prompt hacking and some of the defenses that are used to address the potential consequences of its use.
- Participant:
- Presenter: Ray Villalobos
- Notes:
- 10/17/2023
- Access Restriction:
- Restricted for use by site license.
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.