Tensor Trust @TensorTrust

The competitive prompt injection game: https://t.co/pZOoC07VIx By @sdtoyer @OliviaGWatkins2 @EthanMendes3 @justinsvegliato @LukeBailey181 @cnnmonsugar @isaacongjw tensortrust.ai Joined August 2023

Tweets

13
Followers

72
Following

9
Likes

8

Learn Prompting @learnprompting

2 years ago

Prompt Injection vs Jailbreaking Is there a difference? Yes!!! From convo with @goodside @simonw @elder_plinius @InterwebAlchemy @KGreshake : 1/5

1 7 24 5K 25

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius

2 years ago

Found a new (to me) competitive prompt-hacking challenge from @TensorTrust and it's quite fun! Couldn't put it down after making an account this morning and climbed from the bottom of the leaderboards to the top 5 (out of 4,000+ accounts). Look out for the SurlyMammoth ;)

3 1 7 407 3

Download Image

Eric R Allen @InterwebAlchemy

2 years ago

Projects have been gathering a lot of data about LLM vulnerabilities via gamification. Join @LakeraAI, @TensorTrust, @learnprompting, and @projectlve for our Lessons Learned from Crowdsourced LLM Threat Intelligence webinar on 2024-01-25 at 18:00 UTC. lakera.ai/event/crowdsou…

0 7 17 2K 2

Sam Toyer @sdtoyer

2 years ago

Prompt injection is a huge security problem for LLM apps. To study this, we built Tensor Trust: a game where you create and defend against prompt injections. We’re releasing a paper + dataset with 70k unique attacks, 40k unique defense prompts, and new robustness benchmarks. 👉

6 43 127 30K 62

Download Video

Tensor Trust @TensorTrust

2 years ago

This looks great! They have a nice taxonomy on page 5 of the paper, released 600k attacks (!!) on their website at paper.hackaprompt.com (some of them could probably be reused on tensortrust.ai as well, since our threat model is very similar)

Louis-François Bouchard 🎥🤖 @Whats_AI

2 years ago

1 3 11 3K 3

Download Image

0 1 5 212 0

Tensor Trust @TensorTrust

2 years ago

This looks great—you can defend with prompts (like Tensor Trust), but also with LLM-based or code-based output filters. The catch is that defenses can't wreck benchmark performance of the LLM, which is a much stricter (and more realistic) constraint than Tensor Trust imposes.

Florian Tramèr @florian_tramer

2 years ago

3 26 99 28K 47

Download Image

0 2 9 1K 1

Tensor Trust @TensorTrust

2 years ago

Tensor Trust just got support for Claude! You can now use GPT 3.5 Turbo, PaLM Chat Bison, or Claude Instant 1.2 to defend your account from prompt injection attacks on tensortrust.ai.

0 2 8 617 1

Download Video

Tanishq Mathew Abraham, Ph.D. @iScienceLuvr

2 years ago

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game abs: arxiv.org/abs/2311.01011 project page: tensortrust.ai/paper "we present a dataset of over 126,000 prompt injection attacks and 46,000 prompt-based “defenses” against prompt injection, all created by…

1 22 95 12K 28

Download Image

Mikolaj Kowalczyk @m1k0ww

2 years ago

Check out this LLM wargame: tensortrust.ai! Super cool, kudos @TensorTrust,@sdtoyer and the rest of the team. #AI #LLM #Hacking

0 2 7 176 0

Tensor Trust @TensorTrust

2 years ago

🎉6,000 attacks submitted today! We've made some changes to keep things moving, including a shorter unlock time (1h) so there are more green accounts to attack, and also a lower penalty for getting broken into. Excited to see your new attacks!

0 2 6 230 0

Download Image

Justin Svegliato @justinsvegliato

2 years ago

Check out our online game #TensorTrust that we made to study #LLMs! At banking.withai.lol, you have a bank account protected by #ChatGPT: you just tell the AI your password🔒 and a few security rules for when to grant access🏦