The competitive prompt injection game: https://xitter.cf/t.co/pZOoC07VIx By @sdtoyer @OliviaGWatkins2 @EthanMendes3 @justinsvegliato @LukeBailey181 @cnnmonsugar @isaacongjw
Joined August 2023
- Tweets13
- Following9
- Followers81
- Likes8
Tensor Trust retweeted
Prompt Injection vs Jailbreaking
Is there a difference? Yes!!!
From convo with @goodside @simonw @elder_plinius @InterwebAlchemy @KGreshake :
1/5
Tensor Trust retweeted
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 ;)
Tensor Trust retweeted
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/crowdsourcin…
Tensor Trust retweeted
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. 👉
Tensor Trust retweeted
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 players of an online game called Tensor Trust. To the best of our knowledge, this is currently the largest dataset of human-generated adversarial examples for instruction-following LLMs."
Tensor Trust retweeted
Check out this LLM wargame: tensortrust.ai! Super cool, kudos @tensortrust,@sdtoyer and the rest of the team. #AI #LLM #Hacking
Tensor Trust retweeted
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🏦
