Adversarial Machine Learning @adversarial_ML

I tweet about #MachineLearning and #MachineLearningSecurity. Joined April 2018

Tweets

14
Followers

182
Following

52
Likes

44

Somesh Jha @jhasomesh

7 years ago

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

0 3 29 0 2

Aleksander Madry @aleks_madry

7 years ago

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)

4 35 107 0 12

Download Image

Joey Bose @bose_joey

7 years ago

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…

1 6 12 0 0

Aleksander Madry @aleks_madry

7 years ago

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

5 61 144 0 9

Download Image

gio @GiorgioPatrini

7 years ago

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

1 8 22 0 2

Download Image

Battista Biggio @biggiobattista

7 years ago

"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 😀

1 8 15 0 0

Ian Goodfellow @goodfellow_ian

7 years ago

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…

6 100 361 0 22

Download Image

Ian Goodfellow @goodfellow_ian

7 years ago

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…

7 175 518 0 50

Download Image

Savan Visalpara @savanvisalpara7

7 years ago

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

0 4 2 0 0

Somesh Jha @jhasomesh

7 years ago

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

2 9 70 0 3

Adversarial Machine Learning @adversarial_ML

7 years ago

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

0 0 1 0 0

Adversarial Machine Learning @adversarial_ML

7 years ago

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