Posts

Posted on

Adversarial Temporary Tattoo – John Compas

Adversarial Temporary Tattoo

Fooling AI for the price of a sticker

John Compas

Abstract

Researchers have consistently demonstrated over the past three or four years that image and facial recognition techniques are highly susceptible to attack. Many are not designed to be robust in such a manner, making them vulnerable. I aim to create temporary tattoos or other articles of clothing that can disguise the wearer from facial or object recognition. Potentially, this tattoo could not only obscure the wearer but force the AI to classify them as a different person or object.

Technical Details

Researchers at Carnegie Mellon showed two years ago that it was possible to create psychedelic looking glasses that could massively impact how that person’s face was classified by AI [1].  Since then a number of different studies have had similar success attacking classifiers using a variety of techniques. An open source project dedicated to this idea, CVDazzle, has produced many “anti faces” to conceal the wearer. However, both Carnegie Mellon and CVDazzle’s techniques are relatively human obvious. I aim to create a temporary tattoo while looking “normal” has slight, human undetectable modifications that obfuscate the user’s face or body to image detection algorithms. This has been done by [2] although solely on a pixel-by-pixel basis and not in the real world.

[3] Turning a banana into a toaster

 

A team at Google found that a small patch, applied near an object, could disrupt image classifiers. Many of these techniques counted on access to the internal workings of the classification algorithm to work, however. In [4] a team from MIT showed that a “black box” approach to attack Google’s Cloud Vision. With an evolutionary algorithm, they were able to reduce the time taken to obfuscate an image by multiple orders of magnitude. Using a combination of the aforementioned techniques, I would aim to create patterns for temporary tattoos. Ultimately, the goal would be a tattoo that would be innocuous to humans, yet potent to a classification algorithm.

An example: what you see, what Google’s Cloud Vision or FaceID sees

Actually fabricating the tattoos would be trivial. Tattoo paper is cheap and widely available for use with color printers. Likely the most challenging aspect of the project would be to translate simulated pattern success into a real-world demonstration where the lighting and shadows are inconsistent.

Potentially, other objects and fabrics could be demonstrated, but their fabrication is more challenging.

Goals

The purpose of this project is more experimental. Attempts will be made to make these tattoos look normal, but the main purpose will be to successfully attack commercial face recognition technology.

Applications

The implications of this technology, if successful, are widespread. By simply concealing a wearer’s face, security technology at airports and face-ID technology in large cities like London or New York could be massively compromised for little investment.

If fooling a classifier into recognizing you as a different person is also possible, a whole host of new vulnerabilities are exposed. For example, if Apple’s face ID can be exploited, phones and iPads would instantly be vulnerable.

Confident Skills:

Programming (variety of languages)

Hardware Design, PCB Layout

3D Printing

Laser Cutting

Not Confident:

Sewing

Clothing Design

AI

References

[1] https://www.cs.cmu.edu/~sbhagava/papers/face-rec-ccs16.pdf

[2] https://arxiv.org/pdf/1804.04779.pdf

[3] https://arxiv.org/pdf/1712.09665.pdf

[4] https://arxiv.org/pdf/1712.07113.pdf

 

Posted on

Project Pitch – Yudong Huang

Synchronization Suit

For the final project, I would like to make a synchronization suit that could assist people with needs of learning poses and moves. In general, it provides wearers with feedback of what part of body to move and where to move. Therefore, it could be helpful especially for performers needing to synchronize their moves.

A good example of how synchronization suit could be useful is learning a dance. As a dancer, I have been leading practices and teaching a dance routine for times, and it really takes me a lot of energy and time. If we could have a wearable tech that provides everyone in a team with feedback of how to move their body in ream time, it could improve whole team’s efficiency and save a lot of time. The idea was first inspired by the yoga learning helper mentioned in class discussion.

Functions

Following are tow main function modes of the suit I could imagine so far.

Real Time Feedback – Each sync suit could be set as a teacher or a learner. When set as learner, it receives signals from a suit set as teacher, and tells the wearer whether his or her moves is synchronized with the teacher. This mode should work when there are more than one suits.

Pre-Record Moves – When working alone, the suit allows the wearer to record a sequence of moves (ex. a dance, a fitness move-pattern) which could be later used to compare with moves of another wearer (either send to another suit or give the suit to another wearer). At the end of comparing, the suit would tell a sync rate to the user as result.

Implementation

Here are some choices I would have to make or difficulties I would face with making the suit.

How to collect data of teacher’s moves? – I think sensors that could collect information of position change would be very helpful in this case. To as clear as much draw the moves of teacher’s whole body, sensors would be placed at each key joint of human body (ex. wrist, elbow, shoulder, chest, crotch, knee).

Feedback should be provided in what ways? – As the wearer could potentially teach / learn numbers of poses and moves, the way of giving feedback should be simple enough and feedback should be easy enough to get no matter in what poses. So far the idea I have come up with is that there would be lighting lines along the side of arms and legs to work as the real time feedback giver. Whether the part of body is in the correct position would be shown in binary colors (ex. green for yes and red for no), and because the lighting lines are along the side of whole body, they already cover the largest space they could cover, which might be easy enough to see.

In what ways to tell wearer the position to move? – This would probably be the hardest part of making the suit. Should the guiding be told visually, or guiding should be transmitted physically through  a light force on body? This is an important choice and should be considered and discussed further.

Other Thoughts

As colors are displayed based on whether moves are synchronized, this might be made use of in performing and creating a different visual experience.

Maybe choreographs or move patterns could be designed and edited in software and imported into the suit in the future.

Posted on

Experimental Materials Development

Michael Sachen

(1) Hypar Pleating

What would one need to accomplish this?

I have- Sewing and Pleating experience

We need- Chemistry skills, i.e. how can we isolate the active ingredient in hair perm product or similar chemicals to permanently set pleats?

What if it doesn’t work? Polyester!

(2) Experimental Dyes

(a) Metal Deposition

By making a soluble metal solution, make it possible to embed metal into fabrics… Who knows the uses?

Fabric that rusts?

Metal color dyes?

What I have- Dye knowledge

What I don’t have- Deep knowledge on metals

 

Bacteria Dye

Chromatophores, Carotenoids, and Chlorophyll Variants, and PH variation..

Work has been done in this area, but  aim to create a semi exhausted attempt to catalog the process of Bacteria dye. What variants change the color and properties of the bacterial dye

 

Posted on

Initial Project Pitch – Sungjin Park

Sungjin Park

Project Description

  • My initial project idea is to make wearable glove that measures heart rate. My primary goal is to hide wires and sensors underneath the outer thread by making double layers of wools in the back of the glove. For better movement and stable functionality, positioning Arduino would be a key concern for this project. Since this project is meant to be pragmatic, subtle design would be a crucial part when implementing wires and sensors. My target potential wearers are people with high blood pressures and athletes so they can check their heart rate at any time. The most challenging part will be a choice of material. Since my target wearers vary in activities, I have to find proper material that falls between wool and spandex for both daily use and active use purpose.

Confident skill set

  • Programming

Weak skill set

  • Designing, stitching, and manipulating hardware

Function

  • It will transmit wearers’ heart rate to their phone consistently and measure hourly peak and low point recorded just like built-in pedometer in iphone.

Concept art

Posted on

Project Pitch – Vedant

Project Description:

For the final class project, I would like to make smart gloves that helps the user send remote signals using hand gestures as commands. While these gloves could have many functions, I would like to focus on using these gloves as part of a smart home, including functions like controlling the TV, smart lights, as well as a Google Home/Alexa (through a speaker). This could especially be useful for people with disabilities, or even just a very lazy person.

While there are many similar kinds of gloves that exist as projects, a lot of those gloves do not make use of the wide variety of sensors available in the market. Additionally, some of the projects seemed to be made inefficiently in that they seemed to be pretty bulky for how much they can do. I want to explore how those existing gloves could be improved in not just functionality but also aesthetics. Thus, I would work on this project not as an invention, but rather a demonstration/experiment.

The functionality of the glove would include things like a force sensitive/capacitive touch option where a user could clap to turn on/off lights, as well as gesture-controlled commands that can control TV functions.

Sketch:

 

Inspirations:

https://www.youtube.com/watch?v=yOb07ZfrYUk

http://maestroglove.com/

https://ieeexplore.ieee.org/document/6629884

 

Materials/Tools:

Gloves

Sensors: flex sensor, gyroscope, capacitive touch/force sensors

Infrared LED emitter/receiver

Microcontroller- adafruit flora, particle photon, arduino

Possible 3d printed housings/case for the electronics

 

Skills/concepts

While I have some experience with programming, this project would require a lot of microcontroller programming, so that would be the main thing I would have to master. The project would also require some knowledge of IoT so I would be looking more into that as well.

Additionally, I have experience using tools in the makerspace (3d printing, laser cutting), so if I have time to focus on the aesthetics, I could use those skills to help me improve the looks. However, it is a given that I will also have to learn soldering well to compact my design, as well as sewing to make the glove look nice.

 

Timeline

March 16: The sensor inputs can be used to output various signals to the devices

April 4: The sensors are integrated into a glove

April 20: The glove is a lot sleeker than the first prototype, and improvement in error reduction

Posted on

Project Pitch – Junda Chen

Musical Jacket

Summary

Musical Jacket that allows musician to freely play and record music is an attractive idea for me. For now I envision a realistic implementation that support the record, play and output of the music by MIDI keyboard-like structure attached on the front of the jacket.

I am open to idea that related to other idea under category “aesthetic, conceptual, data driven/AI, musical”. I think the musical jacket, though not a brand new idea, is quite useful and straight forward to implement (at least as it seems to be right now). I would therefore love to connect to other ideas that could make the jacket more pragmatic and aesthetic.

Slides for introduction

Posted on

Initial Project Pitch

Smart Knee Sleeve

Jake Cordover

 

Rehabbing from significant knee injuries/surgeries consists of different therapuetic protocols that almost always involve regaining knee flexion and extension. Consequently, physical therapists are tasked with hitting certain flexion/extension milestones throughout a recovery, however— the failure to adhere to such milestones (too much or too little) can result in lifelong loss of function.

Currently knee flexion and extension is measured with a device called a Goniometer. Goniometers are accurate and work well in clinical settings, however when patients go home and complete exercises and live their day to day lives, a Goniometer becomes of little use— hence the Smart Knee Sleeve.

The Smart Knee Sleeve is a soft, functional knee sleeve. By using strategically placed stretch sensors, the knee sleeve will communicate with devices, feeding live flexion and extension data. Patients at home can feel comfortable flexing and extending legs, knowing they are within the confines of the therapists recommended allowances. Therapists will be granted insights into how patients are completing their exercises and if there is too much or too little mobility.

However, applications of the Smart Knee Sleeve are not confined to injury rehabilitation. Additional, pragmatic applications include: examining data to deduce mechanism of injury perhaps allowing for better diagnosis, flagging data extrema as something that should be pursued further, a comparative tool to make sure both legs are performing in similar manner, a performance enhancing tool to coach proper form and alignment in various sporting activities, and many, many more applications.

Potential consumers could vary from athletes recovering from injury, to athletes wishing to find data as a performance boost, to older patients simply trying to recover to regain normal function. As a soft, functional sleeve, this device will appeal to many people, in all stages of activity.

For the execution of this project, I am confident in coding and handling data. I also have had exposure the the medical aspect of this project. I am less confident in designing and handling the physical componentry as well as the different aspects in creating a comfortable, sleek garment.

Posted on

Project Pitch – Julia Kosier

I would like to create a chameleon-inspired shirt; the wearer will touch objects to change the shirt’s color to that of the object. This would be done utilizing a color sensor and a series of LEDs.

To minimize the look of distinct LEDs and make the color look as smooth as possible, the shirt would have two layers; a base layer, which has the electrical components (sensor, microcontroller, and LEDs), and a top layer made of a light diffusing fabric that would hopefully help to even out the light and make it look more like the shirt is one continuous color.

Rather than attempting to solve a problem, this project is meant to be an interesting aesthetic display. The potential consumer is someone who wants a unique statement piece for their wardrobe.

I’m confident I have the skills for any programming required. I’m less confident about the electronics, the sewing, and, as is probably apparent from my sketches, the design/aesthetics of the garment.

Posted on

Project pitch

Wireless charging jeans pocket

Gregg Van Dycke

  • The problem I am trying to solve is the having to stop your day to charge your phone. With phones being more and more powerful and batteries still being a last consideration in phone design. Heavy users often have to recharge their phone at least once per day. That can be a hassle, and you oftentimes have to carry a separate charger around.
  • The project is meant to be both experimental as well as playful. It will be interesting to see the feasibility of having a wireless charging in one’s pocket in terms of comfort as well as effectiveness.
  • The potential consumer for this product will be someone that is busy and is not able to sit around and wait for their phone to charge. Or someone that is a heavy phone user that is looking to extend their phones battery life without having to connect it with a cable or set it down to charge a standard wireless charger.

Some aspects of the project that I am confident in are any programming or data collection. I am also some what confident in getting hardware to work together.

Some aspects of the project that I have less skills in are sewing and handling different materials. and making it look good. I am not as confident in soldering or advanced electrical circuits.