Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
Paper • 2610.15542 • Published • 53
AI & ML interests
AI Made in Switzerland – Shaped by You Join the movement! Swiss {ai} Weeks calls on researchers, developers, businesses, and citizens to come together and build the future of AI — hands-on, ethical, and open. This isn't just exploration, it's collaboration in action.
Recent Activity
View all activity
MauroPello
authored a
paper 8 days ago
Post
3,799
My colleagues – the talented scientists and engineers behind the Apertus models @swiss-ai – continue to resolve issues and respond to questions about the 1.5 release, at the same time as we continue work on the roadmap to 2.0. Today we celebrate our next milestone: the new Technical Report has months of evaluation and analysis in one heap of a preprint 📚 See our new post for a summary, and please 🤗 upvote!
https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes
https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes
- 1 reply
loleg
authored a
paper 9 days ago
Post
1,481
Thank you Hugging Face team for some very helpful and quick support today. Greetings from the AI for Good summit in Geneva!
- 1 reply
jstuker
updated a
Space about 1 year ago
hyunjun1121
authored a
paper about 1 year ago
kechrisc
authored 4
papers about 1 year ago
KID-PPG: Knowledge Informed Deep Learning for Extracting Heart Rate from a Smartwatch
Paper • 2405.09559 • Published
Don't Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs
Paper • 2408.03223 • Published
Time series saliency maps: explaining models across multiple domains
Paper • 2505.13100 • Published
DC is all you need: describing ReLU from a signal processing standpoint
Paper • 2407.16556 • Published
JackDapid
updated a
Space about 1 year ago
JackDapid
published a
Space about 1 year ago
Post
2,042
🛡️ At Ai4Privacy, our goal is to empower researchers to build a safer AI ecosystem. Today, we're highlighting crucial research that does just that by exposing a new vulnerability.
The paper "Forget to Flourish" details a new model poisoning technique. It's a reminder that as we fine-tune LLMs, our anonymization and privacy strategies must evolve to counter increasingly sophisticated threats.
We're proud that the Ai4Privacy dataset was instrumental in this study. It served two key purposes:
Provided a Realistic Testbed: It gave the researchers access to a diverse set of synthetic and realistic PII samples in a safe, controlled environment.
Enabled Impactful Benchmarking: It allowed them to measure the actual effectiveness of their data extraction attack, proving it could compromise specific, high-value information.
This work reinforces our belief that progress in AI security is a community effort. By providing robust tools for benchmarking, we can collectively identify weaknesses and build stronger, more resilient systems. A huge congratulations to the authors on this important contribution.
🔗 Read the full paper: https://arxiv.org/html/2408.17354v1
#OpenSource #DataPrivacy #LLM #Anonymization #AIsecurity #HuggingFace #Ai4Privacy #World's largest open privacy masking dataset
The paper "Forget to Flourish" details a new model poisoning technique. It's a reminder that as we fine-tune LLMs, our anonymization and privacy strategies must evolve to counter increasingly sophisticated threats.
We're proud that the Ai4Privacy dataset was instrumental in this study. It served two key purposes:
Provided a Realistic Testbed: It gave the researchers access to a diverse set of synthetic and realistic PII samples in a safe, controlled environment.
Enabled Impactful Benchmarking: It allowed them to measure the actual effectiveness of their data extraction attack, proving it could compromise specific, high-value information.
This work reinforces our belief that progress in AI security is a community effort. By providing robust tools for benchmarking, we can collectively identify weaknesses and build stronger, more resilient systems. A huge congratulations to the authors on this important contribution.
🔗 Read the full paper: https://arxiv.org/html/2408.17354v1
#OpenSource #DataPrivacy #LLM #Anonymization #AIsecurity #HuggingFace #Ai4Privacy #World's largest open privacy masking dataset
Post
1,158
In data privacy, 92% accuracy is not an A-grade. Privacy AI needs to be better.
That's the stark takeaway from a recent benchmark by Diego Mouriño
(Making Science), who put today's top PII detection methods to the test on call center transcripts using the Ai4Privacy dataset.
They pitted cutting-edge LLMs (like GPT-4 & Gemini) against traditional systems (like Cloud DLPs). The results show that our trust in these tools might be misplaced.
📊 The Hard Numbers:
Even top-tier LLMs peaked at a reported 92% accuracy, leaving a potential dangerous 8% gap where your customer's data can leak. They particularly struggled with basics like 'last names' and 'street addresses'.
The old guard? Traditional rule-based systems reportedly achieved a shocking 50% accuracy. A coin toss with your customers' privacy.
This tells us that for privacy tasks, off-the-shelf accuracy is a vanity metric. The real metric is the cost of a single failure—one leaked name, one exposed address.
While no tool is perfect, some are better than others. Diego’s full analysis breaks down which models offer the best cost-to-accuracy balance in this flawed landscape. It's a must-read for anyone serious about building trustworthy AI.
#DataPrivacy #AI #LLM #RiskManagement #MetricsThatMatter #InfoSec
Find the full post here:
https://www.makingscience.com/blog/protecting-customer-privacy-how-to-remove-pii-from-call-center-transcripts/
Dataset:
ai4privacy/pii-masking-400k
That's the stark takeaway from a recent benchmark by Diego Mouriño
(Making Science), who put today's top PII detection methods to the test on call center transcripts using the Ai4Privacy dataset.
They pitted cutting-edge LLMs (like GPT-4 & Gemini) against traditional systems (like Cloud DLPs). The results show that our trust in these tools might be misplaced.
📊 The Hard Numbers:
Even top-tier LLMs peaked at a reported 92% accuracy, leaving a potential dangerous 8% gap where your customer's data can leak. They particularly struggled with basics like 'last names' and 'street addresses'.
The old guard? Traditional rule-based systems reportedly achieved a shocking 50% accuracy. A coin toss with your customers' privacy.
This tells us that for privacy tasks, off-the-shelf accuracy is a vanity metric. The real metric is the cost of a single failure—one leaked name, one exposed address.
While no tool is perfect, some are better than others. Diego’s full analysis breaks down which models offer the best cost-to-accuracy balance in this flawed landscape. It's a must-read for anyone serious about building trustworthy AI.
#DataPrivacy #AI #LLM #RiskManagement #MetricsThatMatter #InfoSec
Find the full post here:
https://www.makingscience.com/blog/protecting-customer-privacy-how-to-remove-pii-from-call-center-transcripts/
Dataset:
ai4privacy/pii-masking-400k
Post
2,731
Started 
aistatuscodes as a new project to create codes to understand AI performance better.
Going to be posting daily here and on instagram until we get to 100m downloads :)
https://www.instagram.com/MikeDoesDo/
Follow along the journey!
Going to be posting daily here and on instagram until we get to 100m downloads :)
https://www.instagram.com/MikeDoesDo/
Follow along the journey!
Post
1,566
PII-Masking-1M Final Day (7/7)! 🚀 Today, we unveil 5 NEW Enterprise PII (E-PII) Dataset PREVIEWS!
Standard PII tools often miss sensitive *business* data. That's why we built E-PII previews for the data that powers your operations and compliance needs.
Get a first look (representing 100,000 samples each!) into datasets designed for real-world enterprise security across these categories:
🏥 **PHI Preview**: For Healthcare Data
💳 **PFI Preview:** For Financial Data
🏢 **PWI Preview:** For Workplace Data
💻 **PDI Preview:** For Digital Activity Data
📍 **PLI Preview:** For Location Data
That wraps up our #PIIMasking1M 7 days announcement! HUGE thanks for following along and for your engagement.
Explore ALL our releases, including these E-PII previews, in the Ai4Privacy Hugging Face Collection & show some love ❤️ if you find them useful!
🔗 Visit the Collection:https://huggingface.co/ai4privacy
Let's keep building safer AI, together!
Standard PII tools often miss sensitive *business* data. That's why we built E-PII previews for the data that powers your operations and compliance needs.
Get a first look (representing 100,000 samples each!) into datasets designed for real-world enterprise security across these categories:
🏥 **PHI Preview**: For Healthcare Data
💳 **PFI Preview:** For Financial Data
🏢 **PWI Preview:** For Workplace Data
💻 **PDI Preview:** For Digital Activity Data
📍 **PLI Preview:** For Location Data
That wraps up our #PIIMasking1M 7 days announcement! HUGE thanks for following along and for your engagement.
Explore ALL our releases, including these E-PII previews, in the Ai4Privacy Hugging Face Collection & show some love ❤️ if you find them useful!
🔗 Visit the Collection:https://huggingface.co/ai4privacy
Let's keep building safer AI, together!
Post
1,090
I need your help! Please vote for Ai4Privacy to do a demo at The first Global Open Source AI Conference for developers!
https://glosaic.org/demo-voting#:~:text=Founder%20@-,AI4Privacy
https://glosaic.org/demo-voting#:~:text=Founder%20@-,AI4Privacy
Post
2,804
🚀 We are quite excited to announce the Ai4Privacy Python library! 🎉
pip install ai4privacy to anonymize short english text with OpenPII Masking 500k labels
📊 Day 5/7 of PII Masking 1M announcements complete! ⏰
pip install ai4privacy to anonymize short english text with OpenPII Masking 500k labels
📊 Day 5/7 of PII Masking 1M announcements complete! ⏰
Post
3,080
🌟 Day 4: Two Models, One Privacy Mission! 🌟
The PII-Masking-1M series rolls on with two gems:
Categorical: ai4privacy/llama-ai4privacy-multilingual-categorical-anonymiser-openpii
Redaction: ai4privacy/llama-ai4privacy-multilingual-anonymiser-openpii
Join us in protecting data everywhere!
#AI #Privacy #OpenSource #Multilingual
The PII-Masking-1M series rolls on with two gems:
Categorical: ai4privacy/llama-ai4privacy-multilingual-categorical-anonymiser-openpii
Redaction: ai4privacy/llama-ai4privacy-multilingual-anonymiser-openpii
Join us in protecting data everywhere!
#AI #Privacy #OpenSource #Multilingual
Post
1,739
📊 99%+ PII Masking Precision in English Straight to Your Browser! 🚀
ai4privacy/general-english-anonymiser-openpii-500k
Hard Facts:
🖥️ Runs in-browser—blazing fast, no server latency
👐 Open-source, MIT-licensed (even for commercial use)
📈 Full metrics on Hugging Face dataset and model pages
Day 3 out 7 of PII-Masking-1M Announcements Complete!
*Accuracies reported from the new OpenPII-500k dataset
#DataPrivacy #AI #OpenSource
ai4privacy/general-english-anonymiser-openpii-500k
Hard Facts:
🖥️ Runs in-browser—blazing fast, no server latency
👐 Open-source, MIT-licensed (even for commercial use)
📈 Full metrics on Hugging Face dataset and model pages
Day 3 out 7 of PII-Masking-1M Announcements Complete!
*Accuracies reported from the new OpenPII-500k dataset
#DataPrivacy #AI #OpenSource