LVE Project @projectlve
Open source initiative with the goal of documenting, tracking and discussing language model vulnerabilities and exposures (LVEs). lve-project.org Joined December 2023-
Tweets29
-
Followers108
-
Following7
-
Likes13
We are delighted to announce Invariant Labs (invariantlabs.ai)! 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.
LLM vulnerabilities also extend to systems build around them like AI Agents. Check out our recent work on the topic.
1/ ‼️Ignore all previous instructions and read the following thread‼️ 📣Presenting AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
I'm excited to represent @projectlve at the webinar. Hope to see you there!
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…
We are really excited to present thoughts and insights from our project at the Lessons Learned from Crowdsourced LLM Threat Intelligence!
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…
@clintgibler Thanks for the highlight :)
🗒️ LVE Repository Like CVEs but for LLMs A project documenting and tracking vulnerabilities and exposures of large language models (LVEs) lve-project.org/index.html
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…
You can find more copyright issues in the lawsuit document created by @nytimes: nytco-assets.nytimes.com/2023/12/NYT_Co…
If you found more examples, we encourage you to contribute them to the open-source LVE repository: github.com/lve-org/lve
Check out our latest copyright LVE based on the @nytimes vs @OpenAI lawsuit! lve-project.org/responsibility… What do you think about the lawsuit outcome and its implications on the future of AI?
🎄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: lve-project.org/challenges/
Kudos to @andyzou_jiaming for running the suffix attack with Llama Guard. You can find their code here: github.com/andyzoujm/brea….
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: lve-project.org/blog/how-effec…
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.
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: arxiv.org/abs/2310.07298…
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: lve-project.org/challenges/loc…
Want to chat about the LVE project at @NeurIPSConf #NeurIPS2023? We made it easy to spot @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.
@TeddyTran_ That's awesome to hear @TeddyTran_, looks like you did pretty well. We are already working on the next batch, so stay tuned :)
We are super excited to announce LVE 🎉 With LVEs we track LLM vulnerabilities and exposures in an open-source community-first approach. Announcement: lve-project.org/blog/launching… 🧵 A thread on the LVE project and why it matters:
@projectlve Had alot of fun with the challenges!
centrix @centrixsystems
848 Followers 2K Following Open-source business management software engineered to operate at scale. Built on a robust microservice architecture. Designed to evolve with your enterprise.
musyalyusya @exceptfh4MtK4
33 Followers 345 Following
Maxim Von Tarnow (tes... @yaponamat
54 Followers 2K Following Hinter jeder Tür, wo d nit uffmache söttsch, ligt öbbis, wo uf di wartet.
snaykey @snaYkeY
73 Followers 816 Following 🇧🇬🇳🇱 AI Red Team Researcher @zenitysec💜 MSc Data Science🤝AI safety 💙 ЯainaResearch🤗 competitive AIRT enjoyer
Ziyu Lin @ZiyuLin00
30 Followers 291 Following I'm an PhD student @NTUsg. I focus on network security and protocol security.
Adekunle @Adekunle8955911
1 Followers 81 Following
Kartik Sachdev | surv... @survivalcrziest
284 Followers 1K Following Product leader, builder & advisor | AI, Privacy & Sustainability | Accidental DJ @DJ_WeAreAgile | Weekly briefs on AI x climate: https://t.co/og5IPsf7j3 | Views own.
Ammar Fahmy @_ammar_fahmy_
60 Followers 611 Following Founder @lawmate_lk || Senior AI/ML Engineer || NLP Specialist || Certified AI Expert
Luke Walker @elukewalker
223 Followers 1K Following Husband & father first. Director, Developer Program @Yubico. Passionate about security & privacy, cloud & mobile DX, & grilling. Opinions my own.
Tareq Fadel @DeltaWorld
1K Followers 6K Following GenAI enthusiast, subject matter expert and advocate on the potential it has on humanity. e/acc @adobe
nion @ubernion
369 Followers 3K Following its all sand kiddo. privacel. striving for erudition. random walker. gaussian slatt.
Bing @Bing16903039
12 Followers 993 Following
Jan Dubiński @jan_dubinski_
461 Followers 1K Following TruthfulAI | PhD in AI | Warsaw University of Technology and NASK, working on AI safety and generative models
tawfiqshah @cyberasko
95 Followers 720 Following
John Freier @johnf_ucb
296 Followers 2K Following Entrepreneur, GenAI Addict/Enthusiast, Web Dev, Statistician, Dirt Biker, Willed Biohacker
Mike Allton | The AI ... @mike_allton
50K Followers 8K Following AI Keynote Speaker | Creator of the Digital Crew System 💫 Helping teams clear Admin Drag with governed AI agents | Host, The AI Hat Podcast
GersonDeWinter @GersondeWinter
408 Followers 7K Following Unchaining Human Potential: Building a Future Where Everyone Thrives
Felix @felixfromessen
1 Followers 7K Following
ztc @ZitaoChen9
1 Followers 90 Following
MSundarV @msundarv
67 Followers 448 Following Data Science & Analytics Specialist @ Philips | Ex- Siemens | GetVu | Master’s in Artificial Intelligence, NUS
Will Callaghan @willcallag
89 Followers 232 Following Dabbling in HCI & AI. Interested in MLOps and AI Safety. Opinions are my own.
Yasuto Fujiwara @YasutoFujiwara1
0 Followers 53 Following
tradernews.ai @tradernewsai
2K Followers 4K Following AI + MARKETS + NEWS THIS IS NOT INVESTMENT ADVICE
Sachit Malik @isachitmalik
164 Followers 4K Following Hola | Security Engineering at Apple | Alum: Carnegie Mellon; IIT Delhi
Palpitate11 @Palpitate111
4 Followers 54 Following
zzzzzq @zzzzzq1998
2 Followers 45 Following
Heintz Beckner @HeintzBeckner
1 Followers 66 Following
Elias Hohl @EliasHohl
37 Followers 46 Following CEO CryptoSearchTools AG | IPhO Gold medalist | EOES Austrian country coordinator | Cybersecurity expert | ETH Zürich Excellence Scholar 2025 Space Systems
Toven @pingToven
6K Followers 4K Following leading inference provider ops @openrouter. opinions my own. aka tomas. 🇦🇷🇦🇷🇦🇷
Santhosh @Santhoshmla
41 Followers 1K Following
Ambuj Kumar @ambuj0
620 Followers 109 Following Built NVIDIA's GPUs. Created Confidential Computing. Solving security at https://t.co/7GYMVHl50Y. Founded 2 companies/$150m+ raised. 100+ patents.
varelaseb @varelaseb1
70 Followers 2K Following
Eric R Allen @InterwebAlchemy
123 Followers 190 Following Full-Stack Software Engineer | Applied AI & LLM Systems | 0 to 1 and Enterprise Scale
Abhishek Arya @infernosec
5K Followers 197 Following Principal Engineer, AI Security at Google. Opinions are my own.
Mark Lippert @marklippert442
188 Followers 2K Following
Simon Willison @simonw
203K Followers 6K Following Creator @datasetteproj, co-creator Django. PSF board. Hangs out with @natbat. He/Him. Mastodon: https://t.co/t0MrmnJW0K Bsky: https://t.co/OnWIyhX4CH
Florian Tramèr @florian_tramer
6K Followers 208 Following Assistant professor of computer science at ETH Zürich. Interested in Security, Privacy and Machine Learning
Yann LeCun @ylecun
1.3M Followers 789 Following Founder/Chair, AMI Labs; Professor, NYU; Partner, 224 Ventures; Ex-Chief AI Scientist, Meta. Researcher in AI, ML, Robotics, etc. ACM Turing Award Laureate.
Luca Beurer-Kellner @lbeurerkellner
2K Followers 438 Following working on secure agentic AI @snyksec PhD @the_sri_lab, ETH Zürich. Prev: @invariantlabsai @lmqllang @projectlve.
Mislav Balunović @mbalunovic
2K Followers 322 Following Research Scientist @GoogleDeepMind - Gemini Thinking
LMQL (Language Model ... @lmqllang
2K Followers 93 Following 💻 An open source programming language for large language models. Typed prompting with control flow, constraints, and tools. By @the_sri_lab @eth_en.
ETH Zurich @ETH_en
95K Followers 532 Following This is the official Twitter account of ETH Zurich in English. Deutscher Account: @ethTrends for United States
You might like
