0

“Ugly shirt” that makes human silhouettes invisible to neural network AIs

Adafruit 2019 3539

[1910.11099] Adversarial T-shirt! Evading Person Detectors in A Physical World.

It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decision makers by attaching adversarial patches to real objects. However, most of the existing works on physical adversarial attacks focus on static objects such as glass frames, stop signs and images attached to cardboard. In this work, we propose Adversarial T-shirts, a robust physical adversarial example for evading person detectors even if it could undergo non-rigid deformation due to a moving person’s pose changes. To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to non-rigid objects such as T-shirts. We show that the proposed method achieves 74% and 57% attack success rates in digital and physical worlds respectively against YOLOv2. In contrast, the state-of-the-art physical attack method to fool a person detector only achieves 18% attack success rate. Furthermore, by leveraging min-max optimization, we extend our method to the ensemble attack setting against two object detectors YOLO-v2 and Faster R-CNN simultaneously.

Read more, PDF, video .. .via Bruce Sterling and William Gibson. Also check out the short story “BLIT” and “Fantasy & Science Fiction v031n06 (1966 12) Von Goom’s Gambit by Victor Contoski.”


Ugly

Shirt appearing on https://mooteef.com/ in 3,2,1…


Stop breadboarding and soldering – start making immediately! Adafruit’s Circuit Playground is jam-packed with LEDs, sensors, buttons, alligator clip pads and more. Build projects with Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE. Circuit Playground Express is the newest and best Circuit Playground board, with support for CircuitPython, MakeCode, and Arduino. It has a powerful processor, 10 NeoPixels, mini speaker, InfraRed receive and transmit, two buttons, a switch, 14 alligator clip pads, and lots of sensors: capacitive touch, IR proximity, temperature, light, motion and sound. A whole wide world of electronics and coding is waiting for you, and it fits in the palm of your hand.

Join 16,000+ makers on Adafruit’s Discord channels and be part of the community! http://adafru.it/discord

Have an amazing project to share? The Electronics Show and Tell is every Wednesday at 7:30pm ET! To join, head over to YouTube and check out the show’s live chat – we’ll post the link there.

Join us every Wednesday night at 8pm ET for Ask an Engineer!

Follow Adafruit on Instagram for top secret new products, behinds the scenes and more https://www.instagram.com/adafruit/

CircuitPython – The easiest way to program microcontrollers – CircuitPython.org


Maker Business — How to start, manage, and fund a paid membership program

Wearables — Make a list of everything you want

Electronics — 1k1? 4R7? Whaaa?

Biohacking — Vitamin-C + Gelatin for Accelerated Recovery

Python for Microcontrollers — Everyone gets a CLUE with CircuitPython! Python’s Next Decade and Us… #Python #Adafruit #CircuitPython @circuitpython @micropython @ThePSF @Adafruit

Adafruit IoT Monthly — Physical Event Notifiers, Particle deprecates Particle Mesh and More! #Adafruit #IoT @Adafruit @AdafruitIO

Microsoft MakeCode — Through the Classroom Door with LEGO Line Follower!

Get the only spam-free daily newsletter about wearables, running a "maker business", electronic tips and more! Subscribe at AdafruitDaily.com !



No Comments

No comments yet.


Leave a comment

Adafruit has a "be excellent to each other" comment policy. Help us keep the community here positive and helpful. Stick to the topic, be respectful of makers of all ages and skill levels. Be kind, and don't spam - Thank you!

Prove you are human by reading this resistor:

0Ω+/- 5%

0
0
1
2
3
4
5
6
7
8
9

0
0
1
2
3
4
5
6
7
8
9

0
0
1
2
3
4
5
6
7
8
9

5
5
10

Prove you are human by reading this resistor:


Click/tap drag the number in the circle of each slider on the left to the matching color band on the resistor.

Can't view resistor colors? Don't worry! Just type your comment and hit submit without moving the sliders. Our moderators will review and approve in a jiffy.

Click Here for a new resistor image.

New to electronics? Click here to learn how to read resistor values.

Or learn to read resistors by playing Mho's Resistance!