LVE Project

Open source initiative with the goal of documenting, tracking and discussing language model vulnerabilities and exposures (LVEs).

[Invariant Labs @InvariantLabsAI]

We are delighted to announce Invariant Labs (https://t.co/LmpeFoA42q)! Our mission is to make AI agents secure and reliable! It is founded by @mvechev, @mbalunovic, @lbeurerkellner, @marc_r_fischer, @florian_tramer and builds on years of experience in industry and academia.

[LVE Project @projectlve]

LLM vulnerabilities also extend to systems build around them like AI Agents. Check out our recent work on the topic.

[Edoardo Debenedetti @edoardo_debe]

1/ ‼️Ignore all previous instructions and read the following thread‼️

📣Presenting AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

[Marc Fischer @marc_r_fischer]

I'm excited to represent @projectlve at the webinar. Hope to see you there!

[LVE Project @projectlve]

We are really excited to present thoughts and insights from our project at the Lessons Learned from Crowdsourced LLM Threat Intelligence!

[Eric R Allen @InterwebAlchemy]

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.

https://t.co/3mqVFRphvE

[LVE Project @projectlve]

@clintgibler Thanks for the highlight :)

[Clint Gibler @clintgibler]

🗒️ LVE Repository

Like CVEs but for LLMs

A project documenting and tracking vulnerabilities and exposures of large language models (LVEs)

https://t.co/KWBsLhTJ0x

[Eric R Allen @InterwebAlchemy]

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.

https://t.co/3mqVFRphvE

[LVE Project @projectlve]

You can find more copyright issues in the lawsuit document created by @nytimes: https://t.co/FUL515rPGj

[LVE Project @projectlve]

Check out our latest copyright LVE based on the @nytimes vs @OpenAI lawsuit!

https://t.co/FGbownhtz3

What do you think about the lawsuit outcome and its implications on the future of AI?

[LVE Project @projectlve]

If you found more examples, we encourage you to contribute them to the open-source LVE repository: https://t.co/9VhQV5SFlY

[LVE Project @projectlve]

🎄For the festive season, we have added a number of bonus levels to the current batch of LVE community challenges.

Have a look, and help us red team LLMs in the process!

Happy holidays everyone!

LVE Challenges: https://t.co/oyGRoOu718

[LVE Project @projectlve]

Kudos to @andyzou_jiaming for running the suffix attack with Llama Guard. You can find their code here: https://t.co/eIkKRJGHnM.

[LVE Project @projectlve]

LLM safety filters like Purple Llama promise responsible and safe deployment of AI, but how effective are they?

In our new blog post, we argue that LLM-based filters are clearly flawed, and that they set up a dangerously circular safety narrative.

Blog: https://t.co/TeJ3PvomXh

[LVE Project @projectlve]

Participate in our Location Inference challenge, to help us collect insights on how deep this capability impacts the safety of responsible LLM deployments.

All submitted solutions are published as part of the LVE project, for the community to benefit and learn from.

[LVE Project @projectlve]

Did you know that you can abuse LLMs to infer a person's location from just a simple online comment?

We demonstrate this in our Location Inference challenge, and show how LLMs can be abused to spy on people, even WITHOUT their consent.

Challenge: https://t.co/NFNHlJgJkO

[LVE Project @projectlve]

LLMs can also infer other private attributes and do so with similar accuracy as humans.

But LLMs are also much cheaper and faster. This enables new forms of online profiling and privacy violation at scale, posing a significant safety risk.

Paper: https://t.co/dlKuKr8kap

[LVE Project @projectlve]

Want to chat about the LVE project at @NeurIPSConf #NeurIPS2023?

We made it easy to spot @marc_r_fischer.

[Marc Fischer @marc_r_fischer]

As you can tell from my previous Tweet I'm making my way to NOLA for @NeurIPSConf #NeurIPS2023.

Happy to chat about @lmqllang, @projectlve, my papers (🧵👇) and trustworthy/safe AI in general.

[LVE Project @projectlve]

@TeddyTran_ That's awesome to hear @TeddyTran_, looks like you did pretty well.

We are already working on the next batch, so stay tuned :)

[LVE Project @projectlve]

We are super excited to announce LVE 🎉

With LVEs we track LLM vulnerabilities and exposures in an open-source community-first approach.

Announcement: https://t.co/aNqG4HoL2s

🧵 A thread on the LVE project and why it matters:

[Teddy @teddytran]

@projectlve Had alot of fun with the challenges!