System and method for distinguishing human swipe input sequence behavior
Recording, analyzing and categorizing of user interface input via touchpad, touch screens or any device that can synthesize gestures from touch and pressure into input events. Such as, but not limited to, smart phones, touch pads and tablets. Humans may generate the input. The analysis of data may include statistical profiling of individual users as well as groups of users, the profiles can be stored in, but not limited to data containers such as files, secure storage, smart cards, databases, off device, in the cloud etc. A profile may be built from user/users behavior categorized into quantified types of behavior and/or gestures. The profile might be stored anonymized. The analysis may take place in real time or as post processing. Profiles can be compared against each other by all the types of quantified behaviors or by a select few.
1. A method of using behavioral biometric algorithms implemented on a computer to authenticate user operation comprising:
a. using a pinpad entry device identifying behavioral traits based on at least three of the following:
i. an angle of the swipe when entering or leaving one or more measuring points,
ii. a velocity between one more measuring points,
iii. an acceleration between one or more measuring points,
iv. a quotient between one or more measuring points,
v. a sequence between multiple measuring points,
vi. a start sequence to a first measuring point,
vii. an end sequence from last measuring point,
viii. a flight between one or more measuring points, the dominant side between one or more measuring points,
ix dominant side between one or more measuring points,
x. an area between one or more measuring points,
xi. a curve fitting between one or more measuring points, xii. a heat map between one or more measuring points;
xii. the average time of the sample,
xiii. keypress timings; and
b. filtering the selected behavioral traits based on at least one of the following:
i. raw data in the highest resolution available for the particular system,
ii. raw data in the resolution determined by the current application,
iii. filtered data fitting different behavior traits;
c. determining shape input sequence from the filtered behavior traits wherein the shape input sequence is the total aggregated distance, time or pressure for a touch input that moves over two or more collision detection shapes and behavior is distinguished by shape contact and direction
d. analyzing the shape input sequence with user profiles to establish at least one of the following:
i. determining if said input sequence is deemed from the same user,
ii. determining if said input sequence is deemed from another user,
iii. determining if said input sequence is deemed not human.
2. The method of claim 1 , wherein said shape input sequence is inputted using a mouse.
3. The method of claim 1 , wherein a raw score of a determination of human characteristics of said swipe input sequence is exhibited, lacking a determination as to whether said swipe input sequence was carried out by a human.
4. The method of claim 1 , wherein collision detection on shapes is used to conduct analysis and distinguish human swipe shape input sequence and behavioral traits from other human behavior and or machine behavior.
5. The method of claim 1 , wherein said shape input sequence comprises a determination of a shape of inputted data based on a shape of at least two letters or numbers.
6. The method of claim 1 , wherein said method is carried out as part of post-processing, after a transaction by a user conducting said swipe input sequence is carried out.
7. The method of claim 1 , wherein a filter is used to omit a part of said input sequence data to anonymize user information.