AI Security Evaluation Research Lightning Talks

Описание к видео AI Security Evaluation Research Lightning Talks

Join us for the award ceremony and lightning talks with the placing submissions of the AI Security Evaluation Research Apart Hacakthon, hosted by Apart Research [https://apartresearch.com/] in May of 2024.

Check out the research pages for the presented projects:
Cybersecurity Persistence Benchmark | Does 'turn it off and on again' work against LLM hackers? ⭢ https://www.apartresearch.com/project...
Say No to Mass Destruction | Will an LLM know when not to answer? ⭢ https://www.apartresearch.com/project...
Dark Patterns in LLMs | Could LLMs be covertly influencing you? ⭢ https://www.apartresearch.com/project...
rAInboltBench | How good are multimodal models at Geoguessr? ⭢ https://www.apartresearch.com/project...

Learn more about the hackathon ⭢ https://apartresearch.com/event/measu...

Our moderator and organizer is Esben Kran and Apart Research.

This video is a slightly trimmed down version of the livestream found at https://youtube.com/live/ZV9Osf0vjSk.

━━━━━ Chapters ━━━━━
00:00 - Intro
02:48 - Cybersecurity Persistence Benchmark
12:05 - Cybersecurity Persistence Benchmark | Questions
14:22 - Say No to Mass Destruction Benchmark |
21:35 - Say No to Mass Destruction Benchmark | Questions
25:44 - Benchmarking Dark Patterns in LLMs
32:31 - Benchmarking Dark Patterns in LLMs | Questions
35:14 - rAInboltBench
45:41 - rAInboltBench | Questions
50:41 - Awards!!
56:44 - Next Steps

━━━━━ Apart Links ━━━━━
Learn more about Apart ⭢ https://www.apartresearch.com
Join future hackathons and sprints ⭢ https://apartresearch.com/sprints
Connect with us on Discord ⭢   / discord  
Check out potential AI safety projects ⭢ https://aisafetyideas.com
Stay up-to-date on Google Calendar ⭢ https://calendar.google.com/calendar/...
Be on the ball with iCal (.ics format) ⭢ https://calendar.google.com/calendar/...
Follow on Twitter ⭢   / apartresearch  
Explore code on GitHub ⭢ https://github.com/apartresearch
Get professional on LinkedIn ⭢   / apartresearch  

Комментарии

Информация по комментариям в разработке