Deep-Spying: Spying using Smartwatch and Deep Learning

نویسندگان

  • Tony Beltramelli
  • Sebastian Risi
چکیده

Wearable technologies are today on the rise, becoming more common and broadly available to mainstream users. In fact, wristband and armband devices such as smartwatches and fitness trackers already took an important place in the consumer electronics market and are becoming ubiquitous. By their very nature of being wearable, these devices, however, provide a new pervasive attack surface threatening users privacy, among others. In the meantime, advances in machine learning are providing unprecedented possibilities to process complex data efficiently. Allowing patterns to emerge from high dimensional unavoidably noisy data. The goal of this work is to raise awareness about the potential risks related to motion sensors built-in wearable devices and to demonstrate abuse opportunities leveraged by advanced neural network architectures. The LSTM-based implementation presented in this research can perform touchlogging and keylogging on 12-keys keypads with above-average accuracy even when confronted with raw unprocessed data. Thus demonstrating that deep neural networks are capable of making keystroke inference attacks based on motion sensors easier to achieve by removing the need for non-trivial preprocessing pipelines and carefully engineered feature extraction strategies. Our results suggest that the complete technological ecosystem of a user can be compromised when a wearable wristband device is worn.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

DEPARTMENT OF ECONOMICS WORKING PAPER SERIES Spying in Multi-market Oligopolies

We consider a multimarket framework where a set of firms compete on two interrelated oligopolistic markets. Prior to competing in these markets, firms can spy on others in order to increase the quality of their product. We characterize the equilibrium espionage networks and networks that maximize social welfare under the most interesting scenario of diseconomies of scope. We find that in some s...

متن کامل

Spying as an Object-Oriented Programming Paradigm

We introduce spying, a novel way of programming with objects, based on capsule programming and reflective facilities. This programming style allows easy building of monitoring systems, such as tracers, debuggers. We point out three main problems related to this programming style, and propose practical solutions to some of them. We exemplify our claims with a system that performs master/slave co...

متن کامل

Spying with the Crowd

The cooperative power of crowd workers has been recently shown to be effective in solving large-scale diverse tasks. We elaborately study one such application of collaborative crowdsourcing. In this paper, we discuss the viability and different facets of crowdspying, activity of spying with the power of crowd workers. This type of citizen involvement has diverse applications that also includes ...

متن کامل

The Economic Costs of Mass Surveillance: Insights from Stasi Spying in East Germany

The Economic Costs of Mass Surveillance: Insights from Stasi Spying in East Germany* Based on official records from the former East German Ministry for State Security, we quantify the long-term costs of state surveillance on social capital and economic performance. Using county-level variation in the spy density in the 1980s, we exploit discontinuities at state borders to show that higher level...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1512.05616  شماره 

صفحات  -

تاریخ انتشار 2015