Conference on Applied Machine Learning for Information Security
Washington, DC
Joined September 2017
- Tweets579
- Following52
- Followers1.2K
- Likes183
Camlis Org retweeted
As @CamlisOrg is wrapping up, reflecting how grateful I am for a tremendous community. The most fruitful plants blossom in rich soil and that's what gives @CamlisOrg its _sui generis_. I and our team at Abundant Security enjoy the benefits of that richness.
Thanks to @UdacityDave and @HZoete/@alxndrdavies for exemplary keynotes, to the authors of well-researched talks and posters, and all of our amazing volunteers for making CAMLIS what it is. I couldn't be more proud of what you've made in this community and event over the last decade.
Camlis Org retweeted
Paper coming soon @CamlisOrg @CrowdStrike
Camlis Org retweeted
Our first blog is live! We spoke to our members about their various interview experiences — the good, the bad, and everything in between.
We’re sharing some of the most actionable insights on what you can do to reduce bias in your interview process!
align-sec.org/blog/reducing-…
Camlis Org retweeted
. @beccalunch presenting on results of our discussions from The Breakfast Club @CamlisOrg
Camlis Org retweeted
The Breakfast Club was a huge success! Thank you to @CamlisOrg for giving us space to connect, talk solutions, and share our insights with the CAMLIS community. See you next year!
In the meantime, connect with us at align-sec.org 💖
Camlis Org retweeted
Feeling #CAMLIS2024 FOMO? Catch the live stream for all CAMLIS talks below 👇
Did you just miss getting tickets? Did you miss your flight? Do you miss being at one of the best single-track conferences on the intersection of ML and infosec? Don't forget you can always catch the live Zoom streams! Links for both days are here: camlis.org/tickets
Camlis Org retweeted
Get ready @CamlisOrg for The Breakfast Club! Swing by for good food, great swag, and even better people!
Camlis Org retweeted
@CamlisOrg is a rewarding and welcoming community. I am so proud to present our work here! Thank you for the incredible questions and feedback! And thank you again to the organisers this year for another stellar event 🤩
Sad another CAMLIS is over… 🥹
Camlis Org retweeted
@rjjoyce8 also @CamlisOrg presenting new datasets and labeling tools for malware types & functionality! arxiv.org/abs/2310.11706 @BoozAllen @umbccsee w/ @cknicholas
Camlis Org retweeted
Someone give Kate H a doctorate already! Finally someone going all in on causal inference for cybersecurity. Super exciting. @CamlisOrg
Camlis Org retweeted
Tirth presenting some of our work @CamlisOrg ! Making test sets harder so that academics can more reliably measure their improvements. @umbccsee @BoozAllen
Camlis Org retweeted
In my opinion security data infra greatest of all time: @kberlin successful infra = successful research @CamlisOrg #camlis2023
Camlis Org retweeted
Its almost time for @CamlisOrg , the best conference at the intersection of ML and Security! We have cupcakes!
Camlis Org retweeted
I’m so glad this is happening again, @NicolasPapernot and @carmelatroncoso!
Same great conference, in Toronto for the April 2024 iteration!
This conference has never been more important for securely scaling the adoption of AI.
This quoted post is unavailable.
Camlis Org retweeted
Get your @CamlisOrg here! Security+ML in archival proceedings.
Amazing work. Thanks authors, and @EdwardRaffML and team!
After much effort, the @CamlisOrg 2022 proceedings are finally up! ceur-ws.org/Vol-3391/ thank you to all authors for helping get the edits needed so that we could finally get this up!
Camlis Org retweeted
After much effort, the @CamlisOrg 2022 proceedings are finally up! ceur-ws.org/Vol-3391/ thank you to all authors for helping get the edits needed so that we could finally get this up!
Camlis Org retweeted
ICYMI - it's quite practical to poison a webscale dataset used by foundation models (for USD $60)..and other tricks.
The defenses are also simple. (...turns out that computing that many hashes can look a lot like crypto mining to behavioral monitoring tools... 😂)
Have you downloaded a large training set (LAION, CC, Wikipedia, etc) in the past to train a machine learning model?
If so, you were vulnerable to an extremely simple and cheap poisoning attack that could have manipulated ~0.02%-0.8% of your dataset
arxiv.org/abs/2302.10149
🧵👇
