Adversarial Machine Learning

I tweet about #MachineLearning and #MachineLearningSecurity.

[Somesh Jha @jhasomesh]

Just read this paper. Short summary: when thinking of defenses to adversarial examples in ML, think of the threat model carefully.

Nice paper. Also won the best paper award at ICML 2018 (@icmlconf )
Congrats to the authors!!

https://t.co/iEdYbZI6VL

[Aleksander Madry @aleks_madry]

Adversarial robustness is not free: decrease in natural accuracy may be inevitable. Silver lining: robustness makes gradients semantically meaningful (+ leads to adv. examples w/ GAN-like trajectories) https://t.co/dynU5RQpM7 (@tsiprasd @ShibaniSan @logan_engstrom @alex_m_turner)

[Joey Bose @bose_joey]

Here's an article by @UofT about our new work on adversarial attacks on Face Detectors that help you preserve your privacy. https://t.co/v2mve80iyD

[Aleksander Madry @aleks_madry]

Think BatchNorm helps training due to reducing internal covariate shift? Think again. (What BatchNorm *does* seem to do though, both empirically and in theory, is to smoothen out the optimization landscape.) (with @ShibaniSan @tsiprasd @andrew_ilyas) https://t.co/Tlo71NSebi

[gio @GiorgioPatrini]

Excited by this direction of formal investigation for adversarial defences: Adversarial examples from computational constraints, Bubeck et al https://t.co/FKUqwuTyE7

[Battista Biggio @biggiobattista]

"No pixels are manipulated in this talk. No pandas are harmed..."
Great ways to differentiate your talk from the rest of talks on adversarial examples... no more pandas please 😀

[Ian Goodfellow @goodfellow_ian]

I'm speaking at the 1st Deep Learning and Security workshop (co-located with @IEEESSP ) at 1:30 today: https://t.co/AaeTVerKNy I'll discuss research into defenses against adversarial examples, including future directions. Slides and lecture notes here: https://t.co/fCcnDo5tib

[Ian Goodfellow @goodfellow_ian]

This paper shows how to make adversarial examples with GANs. No need for a norm ball constraint. They look unperturbed to a human observer but break a model trained to resist large perturbations. https://t.co/m8W1WpQQwu

[Savan Visalpara @savanvisalpara7]

LaVAN: Localized and Visible Adversarial Noise. A method to generate adversarial noise which is confined to small, localized patch of the image without covering any main objects of the image.
https://t.co/QBmMN2hfcL

[Somesh Jha @jhasomesh]

Two papers accepted to ICML 2018. Congrats to all my amazing co-authors. Both on adversarial ML. The arxiv
version of the papers are up, but we will update it soon based on reviewer comments.

Arxiv versions: https://t.co/VoBqhj0jK9 and
https://t.co/gPno2WR0sy

[Adversarial Machine Learning @adversarial_ML]

Link to the paper on PATE- https://t.co/sVE18R9Uwl

[Adversarial Machine Learning @adversarial_ML]

A detailed post on privacy in machine learning describing why do we need private ML algorithms, and how can we leverage PATE framework to achieve the same (by @NicolasPapernot and @goodfellow_ian) https://t.co/qdRiDVV9Qr
#MachineLearning

[Adversarial Machine Learning @adversarial_ML]

Securing Distributed Machine Learning in High Dimensions
https://t.co/XslQZc7VqN
#MachineLearningSecurity #AdversarialML

[Adversarial Machine Learning @adversarial_ML]

IBM Ireland just released "The Adversarial Robustness Toolbox: Securing AI Against Adversarial Threats". This library will allow rapid crafting and analysis of attacks and defense methods for machine learning models.
https://t.co/rzRRLhUZ8H
#MachineLearningSecurity #AdversarialML