-
I got a near fatal rib cramp laughing at this one.
#CleverHans https://twitter.com/drunkhistory/status/1015271688118980614 …
-
Excited for my upcoming talk "Introduction to Observational Coaching" at Mile High Agile 2018 in Denver (5/22, 1:10pm). Awesome for coaches, but also great for Scum Masters and Leaders who want to be more of a coach and less of a coordinator.
#coaching#MHA2018#cleverhans -
I had the great pleasure to talk with
@samcharrington about differential privacy with PATE, and how it aligns with ML. We covered some of the material from the recent#CleverHans blog post (http://www.cleverhans.io/privacy/2018/04/29/privacy-and-machine-learning.html …) Thanks for having me Sam! https://twimlai.com/twiml-talk-134-scalable-differential-privacy-for-deep-learning-with-nicolas-papernot/ …https://twitter.com/samcharrington/status/992133546277048320 …
-
Privacy and ML: two unexpected allies? Read our new
#CleverHans blog post with@goodfellow_ian on how ML researchers can contribute to and benefit from research on differential privacy! Join us at our poster (#11) on PATE tomorrow (Monday) at#ICLR2018http://www.cleverhans.io/privacy/2018/04/29/privacy-and-machine-learning.html … -
The code for Adversarial Patch by Brown et al. is now available on
#CleverHans https://github.com/tensorflow/cleverhans/tree/master/examples/adversarial_patch …pic.twitter.com/NpNkKridrf
-
I've observed SVM classifiers discriminating between music labeled "Classical" and "Disco". It doesn't mean the thing has a lick of musical intelligence though.
#CleverHans -
This is an awesome and very useful contribution to
#CleverHans, thanks@FartashFg et al. !https://twitter.com/FartashFg/status/955606808944627712 … -
MultiGPU adversarial training now in
#cleverhans. Speedup almost linearly with more GPUs up to the number of adversarial steps. Thanks to@goodfellow_ian and Alex Kurakin.https://github.com/tensorflow/cleverhans/tree/master/examples/multigpu_advtrain … -
Este año estaré en Cybercamp con una ponencia y un taller profundizando en mecanismos de seguridad ofensiva y defensiva utilizando
#MachineLearning. Si te interesa el tema nos vemos pronto.#CyberSecurity#TensorFlow#cleverhans#Crypto#stego#game#robots#behavioralanalyticshttps://twitter.com/CybercampEs/status/920273087710494720 …
-
#cleverhans now has an interface common to all attacks, which makes it easy to try out different attacks on a model https://github.com/openai/cleverhans … -
Improvements were recently made to
#cleverhans, including a speed-up for the JSMA attack. Get the latest copy at: https://github.com/openai/cleverhans … -
I will be speaking about adversarial examples and
#cleverhans tonight in Menlo Park. Check for livestream link here: https://www.meetup.com/Data-Mining-for-Cyber-Security/events/237431738/ … -
New
#cleverhans feature: you can now visualize adversarial examples. See tutorial here: https://github.com/openai/cleverhans/blob/master/tutorials/mnist_tutorial_jsma.py … -
We've pushed a few things to
#cleverhans over the last days, grab the last version and keep sending contributions at https://github.com/openai/cleverhans …pic.twitter.com/VZMgoTepGy
-
New
#cleverhans blog post with@goodfellow_ian: "Is attacking machine learning easier than defending it?"http://www.cleverhans.io/security/privacy/ml/2017/02/15/why-attacking-machine-learning-is-easier-than-defending-it.html … -
#cleverhans benchmark#mlearning systems' vulnerability to adversarial w/#Keras +#tensorflow tutorial +#GPU supp. http://bit.ly/2dLhD5b -
#cleverhans tool: “collection of attacks and defenses, along with tutorials on how to use them#AI#OpenAIhttp://qz.com/789071 -
Elon Musk’s
#OpenAI has a new tool:#Cleverhans http://qz.com/789071 .@qz#SelfDrivingVehicles#selfdrivingcars#ElonMusk#innovation#AI
লোড হতে বেশ কিছুক্ষণ সময় নিচ্ছে।
টুইটার তার ক্ষমতার বাইরে চলে গেছে বা কোনো সাময়িক সমস্যার সম্মুখীন হয়েছে আবার চেষ্টা করুন বা আরও তথ্যের জন্য টুইটারের স্থিতি দেখুন।