Adversarial Machine Learning

@adversarial_ML

I tweet about #MachineLearning and #MachineLearningSecurity.

Joined April 2018

14Posts 180Followers 52Following

You might like

@mlsec_lab

@satml_conf

@g_apru

@NicolasPapernot

@ambrademontis

@biggiobattista

@pinyuchenTW

@fbpierazzi

@zyh2022

@drhyrum

@eneelou

@LorenzoCazz

@zangobot

@sotgiu_angelo

@suyafnu

Adversarial Machine Learning reposted

Somesh Jha

@jhasomesh

Jul 5, 2018

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!! arxiv.org/abs/1802.00420

Adversarial Machine Learning reposted

Aleksander Madry

@aleks_madry

Jun 1, 2018

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) arxiv.org/abs/1805.12152 (@tsiprasd @ShibaniSan @logan_engstrom @alex_m_turner)

aleks_madry's tweet image. 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) arxiv.org/abs/1805.12152 (@tsiprasd @ShibaniSan @logan_engstrom @alex_m_turner)

Adversarial Machine Learning reposted

Joey Bose

@bose_joey

May 31, 2018

Here's an article by @UofT about our new work on adversarial attacks on Face Detectors that help you preserve your privacy. news.engineering.utoronto.ca/privacy-filter…

bose_joey's tweet card. New algorithm protects users’ privacy by dynamically disrupting facial recognition tools designed to identify faces in photos

U of T Engineering AI researchers design ‘privacy filter’ for your photos that disables facial...

Source: news.engineering.utoronto.ca

Adversarial Machine Learning reposted

Aleksander Madry

@aleks_madry

May 30, 2018

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) arxiv.org/abs/1805.11604

aleks_madry's tweet image. 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) arxiv.org/abs/1805.11604

Adversarial Machine Learning reposted

gio

@GiorgioPatrini

May 28, 2018

Excited by this direction of formal investigation for adversarial defences: Adversarial examples from computational constraints, Bubeck et al arxiv.org/abs/1805.10204

GiorgioPatrini's tweet image. Excited by this direction of formal investigation for adversarial defences: Adversarial examples from computational constraints, Bubeck et al arxiv.org/abs/1805.10204

Adversarial Machine Learning reposted

Battista Biggio

@biggiobattista

May 24, 2018

"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 😀

Adversarial Machine Learning reposted

Ian Goodfellow

@goodfellow_ian

May 24, 2018

I'm speaking at the 1st Deep Learning and Security workshop (co-located with @IEEESSP ) at 1:30 today: ieee-security.org/TC/SPW2018/DLS/ I'll discuss research into defenses against adversarial examples, including future directions. Slides and lecture notes here: iangoodfellow.com/slides/2018-05…

goodfellow_ian's tweet image. I'm speaking at the 1st Deep Learning and Security workshop (co-located with @IEEESSP ) at 1:30 today: ieee-security.org/TC/SPW2018/DLS/ I'll discuss research into defenses against adversarial examples, including future directions. Slides and lecture notes here: iangoodfellow.com/slides/2018-05…

Adversarial Machine Learning reposted

Ian Goodfellow

@goodfellow_ian

May 22, 2018

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. arxiv.org/pdf/1805.07894…

goodfellow_ian's tweet image. 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. arxiv.org/pdf/1805.07894…

Adversarial Machine Learning reposted

Savan Visalpara

@savanvisalpara7

May 12, 2018

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. arxiv.org/abs/1801.02608

Adversarial Machine Learning reposted

Somesh Jha

@jhasomesh

May 11, 2018

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: arxiv.org/abs/1711.08001 and arxiv.org/abs/1706.03922

Adversarial Machine Learning

@adversarial_ML

Apr 30, 2018

Securing Distributed Machine Learning in High Dimensions arxiv.org/abs/1804.10140 #MachineLearningSecurity #AdversarialML

Adversarial Machine Learning

@adversarial_ML

Apr 29, 2018

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. ibm.com/blogs/research… #MachineLearningSecurity #AdversarialML