Swipe Gesture based Continuous Authentication for Mobile Devices Soumik Mondal NISlab, Gjøvik University College, Norway
Patrick Bours NISlab, Gjøvik University College, Norway
[email protected]
[email protected]
Abstract
tinuous authentication system should, with very high probability, never lock out the genuine user. On the other hand, it should detect an impostor user within a short period of time, to limit the potential damage that can be done by this impostor user to information available on the computer and to limit the disclosure of restricted information. Due to its novelty, little research was done in this area [7, 8, 15]. Continuous Authentication (CA) by analysing the user’s behaviour profile on the mobile input devices is challenging due to limited information and large intra-class variations. As a result, all of the previous research was done as a periodic authentication, where the analysis was made, based on a fixed number of actions or fixed time period [7, 8, 15]. Also, researchers have used special hardware to overcome some of problems [6]. In this research, we will introduce a CA biometric system, which checks the genuineness of the user during the full session. This system uses the behaviour of the user to determine the trust the system has in the genuineness of that user. In particular, it will focus on input of the user’s swipe gestures. The behaviour of the current user will be compared with the stored information about the behaviour of the genuine user and as a result of that comparison the trust of the system in the genuineness of the user will increase or decrease and access to the device will be blocked if the level of trust in the genuineness of the user is too low. We found that the current research on CA reports the results in terms of Equal Error Rate (EER), or False Match Rate (FMR) and False Non Match Rate (FNMR), over either the whole test set or over chunks of a large, fixed number of actions. This means that an impostor can perform a number of actions before the system checks his identity for the first time. This is then in fact no longer CA, but at best Periodic Authentication (PA). In this research, we focus on actual CA that reacts on every single action from a user. The contributions made in this paper are as follows:
In this research, we investigated the performance of a continuous biometric authentication system for mobile devices under various different analysis techniques. We tested these on a publicly available swipe gestures database with 71 users, but the techniques can also be applied to other biometric modalities in a continuous setting. The best result obtained in this research is that (1) none of the 71 genuine users is lockout from the system; (2) for 68 users we require on average 4 swipe gestures to detect an imposter; (3) for the remaining 3 genuine users, on average 14 swipes are required while 4 impostors are not detected.
1. Introduction Due to technological advances we are increasingly dependent on the mobile devices. Such devices are used for banking transactions, therefore they contains highly sensitive information. People use access control mechanisms on mobile devices, like username/password or biometrics, to protect against unauthorized access by another person. This means that a user needs to give proof of his/her identity when starting the mobile device or when unlocking the device. However, in many cases, leave people the device unattended for shorter or longer periods when it is unlocked, or the device can be stolen when it is unlocked. Access control of a mobile device (i.e. smart phone or tablet) is generally implemented as a one-time proof of identity during the initial log on procedure [4, 5, 11]. The validity of the user is assumed to be the same during the full session. Unfortunately, when a device is left unlocked, any person can have access to the same sources as the genuine user. This type of access control is referred to as static authentication. On the other hand, we have Continuous Authentication (also called Active Authentication), where the genuineness of a user is continuously verified based on the activity of the current user operating on the device. When doubt arises about the genuineness of the user, the system can lock, and the user has to revert to the static authentication access control mechanism to continue working. A con-
978-1-4799-7824-3/15/$31.00 ©2015 IEEE
• A novel scheme was introduced on continuous authentication for mobile devices, where the system checks the genuineness of the user on every swipe gesture performed by the user.
458
ICB 2015
• Three different verification processes are used: (1) the system knows all of the imposters; (2) the system knows 50% of the imposters.; and (3) the system doesn’t know any of the imposters.
data are 15 features calculated. Antal et al. [1] show the details of these feature extraction process: (1) Action Duration: The total time taken to complete the action (in milliseconds); (2) Begin X: X-Coordinate of the action starting point; (3) Begin Y: Y-Coordinate of the action starting point; (4) End X: X-Coordinate of the action end point; (5) End Y: Y-Coordinate of the action end point; (6) Distance EndTo-End: Euclidean distance between action starting point and end point; (7) Movement Variability: The average Euclidean distance between points belonging to the action trajectory and the straight line between action starting point and end point; (8) Orientation: Orientation of the action (horizontal or vertical); (9) Direction: Slope between action starting point and end point; (10) Maximum Deviation from Action: The maximum Euclidean distance between points belonging to the action trajectory and the straight line between action starting point and end point; (11) Mean Direction: The average slope of the points belonging to the action trajectory; (12) Length of the Action: The total length of the action; (13) Mean Velocity: The mean velocity of the action; (14) Mid Action Pressure: The pressure calculated at the midpoint of the action; (15) Mid Action Area: The area covered by finger at the midpoint of the action.
• A novel feature selection scheme was proposed. In this research, we will show that the performance reporting measures used in biometrics (FMR and FNMR) are no longer valid for continuous biometrics and we will introduce the Average Number of Genuine Actions (ANGA) and the Average Number of Impostor Actions (ANIA) as new performance reporting measure that can be used to compare continuous authentication systems. We will show how ANGA and ANIA can be computed and how previous results can be transformed to ANGA/ANIA values. The remainder of this paper is organized as follows. In Section 2, we will provide the data description and the feature sets used in this research. We describe the data separation and classification process in Section 3. In Section 4, we will discuss the methodology followed to carry out this research. Result analysis and detail discussion will be provided in Section 5. Finally, we conclude this research with future work in Section 6.
3. Data Separation and Classification
2. Data Description and Feature Extraction
In this section, we discuss the data separation process for our continuous authentication system and the details of the classifiers used on our research.
In our research, we have used a publicly available mobile touch gesture dataset [1]. The complete description of the dataset are given below.
3.1. Data Separation
2.1. Data Description
In our research, we used three verification processes which we describe below. We split the data of each of the users into a part for training and a part for testing. In all cases the classifiers are trained with genuine and impostor (training) data. The amount of training data of the genuine user is 50% of the total amount of data of that user. The training data of the impostor users is taken such that the total amount of impostor data is equal to the amount of training data of the genuine user. This is done to avoid bias towards either the genuine or the impostor class. The three verification processes described below might be seen to correspond with an ”internal system” (VP-1), an ”external system” (VP3) or a combination of both (VP-2). Because the users of Set-2 are a subset of the users of Set-1, are classifiers only trained with data from Set-1 and is all Set-2 data used for testing.
During the data collection process [1] a client-server application was deployed to 8 different Android mobile devices (resolutions from 320x480 to 1080x1205) and touch gesture data was collected from 71 volunteers (56 male and 15 female with ages from 19 to 47). The data was collected in four different session with two different tasks. One task is reading an article and answer some questions about it and another task is surfing an image gallery. The dataset was divided into two sets (i.e. Set-1 and Set-2) were the first set consisted of all 71 users with vertical and horizontal touch gestures. The second set consists of a subset of 51 users (42 male and 9 female) who have more than 100 horizontal gestures. The second set only consists of horizontal gestures data which were not present in first subset. The following raw data is collected during the data collection process [1]: (1) Action Type; (2) Phone Orientation; (3) X-Coordinate; (4) Y-Coordinate; (5) Pressure; (6) Finger Area; and (7) Time Stamp.
3.1.1
Verification Process 1 (VP-1)
In this case the impostor part of the training data is taken from all N (Here, N = 70) impostors and all N impostors contribute approximately with the same amount of data for the training of the classifier. This could for example be
2.2. Feature Extraction In our analysis, we divided the sequence of consecutive tiny movement data into actions (i.e. strokes). From the raw
459
remaining training data will be provided by an external organization. This means that data of impostors of the system will never have been used for training the classifiers. In this case we have two training datasets per genuine user. We did split the group of impostor users into 2 sets of N2 impostors. Figure 3 explain this separation process for the first user, where |Xtr | ≈ |Ytr |. First, we trained the classifiers with the training data of the genuine user and the training data of the first set of N2 impostor users, exactly as we have done in VP-2 (see Figure 3(a)). Next we tested this system with the testing data of the genuine user and all of the data of the second set of N2 impostor users. This process is then repeated with the second set of training data where the impostor users swapping roles (see Figure 3(b)). In this verification process are imposter users not known to the system during testing.
done internally in an organization where all users provide data from training the various classifiers. In this verification process all the imposter users are known to the system. For the testing we used all the data of the genuine user and the impostor users that has not been used for the training of the classifier. This means that we have 1 genuine set of test data and N impostor sets of test data for each user. Figure 1 explains this separation process for the first user, where |Xtr | ≈ |Ytr |. Xtr
Xte 2 3 …
Ytr
N-1 N
Xtr
Figure 1. Data separation for VP-1. This is an example for User 1.
Xte 2 …
Ytr
N/2 N/2 + 1
3.1.2
…
Verification Process 2 (VP-2)
N
This verification process can be seen as a combination of an internal and external system. The classifiers are trained with data from the genuine user as well as data of N2 of the impostor users. In this verification process 50% of the imposter users are known to the system. Also here we test the system with all genuine and impostor data that has not been used for training. For N2 of the impostors this means that their full data set is used for testing, while for the other N2 impostors the full data set with exclusion of the training data is used for testing. Figure 2 explains this separation process for the first user, where again |Xtr | ≈ |Ytr |. Xtr
(a) Xtr … N/2 N/2 + 1 N (b)
Figure 3. Data separation for VP-3. This is an example for User-1.
3.2. Classification After rigorous analysis, we found that 2 regression models performed best for swipe actions. We applied Artificial Neural Network (ANN) [14] and Counter Propagation Artificial Neural Network (CPANN) [2] in a Multi-Modal architecture in our analysis [9]. The score vector we use is (f1 , f2 ) = (Scoreann , Scorecpann ). From these 2 classifier’s scores we calculate a score that will be used in the Trust Model (see Section 4.1) in the following way: For weighted fusion, sc = w1 × f1 + (1 − w1 ) × f2 where, w1 is the weight for the weighted fusion technique.
Xte … N/2 N/2 + 1 … N
Figure 2. Data separation for VP-2. This is an example for User 1.
3.1.3
…
Ytr
2
Ytr
Xte 2
Verification Process 3 (VP-3)
3.2.1 Feature Selection
This verification process can be seen as an external system, where the training and the testing of the system is done by separate sets of impostor users. This could be a situation where a new user will provide his own training data and the
Before building the classifier models we first apply the feature selection technique [10]. Let F = 1, 2, 3, ...m be the total feature set, where m is the number of feature attributes. The feature subset A ⊆ F is based on the maximization of
460
the Sn with Genetic Algorithm as a feature subset searching technique where, A Sn = sup M V CDF (xA g ) − M V CDF (xi )
current action performed by the user as well as on 4 parameters. The parameter A represents the threshold value between penalty and reward. If the classification score of the current action (sci ) is exactly equal to this threshold then ∆T rust = 0. If sci > A then ∆T rust > 0, i.e. a reward is given and if sci < A then ∆T rust < 0, i.e. the trust decreases because of a penalty. Furthermore, the parameter B is the width of the sigmoid for this function (see Figure 4), while the parameters C and D are the upper limits of the reward and the penalty. In Figure 4, we have shown the ∆T rust produced by the Equation 1 based on the classification score of the current action for various sets of parameters.
M V CDF () → M ultivariate Cumulative Distribution F unction xA g → Genuine user f eature subset data xA i → Imposter user f eature subset data
4. Methodology This section describes the methodology we have followed to carry out research.
Algorithm 1: Algorithm for Trust Model. Data: sci → Classification score for the ith action A → Threshold for penalty or reward B → Width of the sigmoid C → Maximum reward D → Maximum penalty Ti−1 → System trust after (i − 1)th action Result: Ti → System trust on the user after ith action begin
4.1. Trust Model The concept of Trust Model was first introduced by Bours [3] in behavioural biometrics based CA. In this model the behaviour of the current user is compared to the template of the genuine user. Based on each single action performed by the current user, the trust in the genuineness of the user will be adjusted. If the trust of the system in the genuineness of the user is too low, then the user will be locked out of the system. More specifically, if the trust drops below a pre-defined threshold Tlockout then the system locks itself and will require static authentication of the user to continue working. The basic idea is that the trust of the system in the genuineness of the current user depends on the deviations from the way this user performs various actions on the system. If a specific action is performed in accordance with how the genuine user would perform the task (i.e. as it is stored in the template), then the system’s trust in the genuineness of this user will increase, which is called a Reward. If there is a large deviation between the behaviour of the genuine and current user, then the trust of the system in the current user will decrease, which is called a Penalty. The amount of change of the trust level can be fixed or variable [3]. A small deviation from the behaviour of the user, when compared to the template, could lead to a small decrease in trust, while a large deviation could lead to a larger decrease. In this research, we implemented a dynamic Trust Model [13]. The model uses several parameters to calculate the change in trust and to return the system trust in the genuineness of the current user after the each separate action performed by the user. All the parameters for this trust model can be user specific. Also, for each user the parameters can be different for different kind of actions. Algorithm 1, shows the proposed Trust Model algorithm. The change of trust (∆T rust ) is calculated according to Equation 1 and depends on the classification score of the
∆T rust (sci ) = min{−D + (
1 C) ), C} exp(− sciB−A )
D × (1 + 1 C
+
(1) Ti = min{max{Ti−1 + ∆T rust (sci ), 0}, 100} (2) end
4.2. System Architecture In this section, we discuss the methodology of our system. The system was divided into two basic phases (see Figure 5). In the training phase, the training data (see Section 3.1) is used to build the classifier models and the models are stored in a database for use during the testing phase (marked as dotted arrow). Each genuine user has his/her own classifier models and training features. In the testing phase, we use the test data which was separated from the training data for comparison. In the comparison, we use the models and training features stored in the database and obtain the classifier score (probability) of each sample of the test data according to the performed action. This score will then be used to update the trust value
461
A = 0.7, B = 0.1, C = 1, D = 1
2
2
1
1 Trust
(sc)
3
0.6
0.8
1
0
0.2
0.4
0.6
0.8
Classifier Score (sc)
Classifier Score (sc)
A = 0.5, B = 0.05, C = 1, D = 1
A = 0.5, B = 0.1, C = 2, D = 2
3
2
2
1
1 Trust
(sc)
3
90
N
N
2
N
3
N
4
5
0 85 0
−1
−1
−2
−2
−3
N
1
∆
∆
0
1
Reset System Trust
0.4
Trust level
0.2
Reset System Trust
95
−3
0
Reset System Trust
−2
−3
Reset System Trust
−1
−2
(sc)
100
0
Reset System Trust
−1
Trust
given in Section 2.
∆
0
∆
Trust
(sc)
A = 0.5, B = 0.1, C = 1, D = 1
3
10
20
30
40
50
60
70
80
90
100
Event Number
Figure 6. Trust for impostor test set.
−3 0
0.2
0.4
0.6
0.8
1
0
0.2
Classifier Score (sc)
0.4
0.6
0.8
1
Classifier Score (sc)
In Figure 6, we see how the trust level changes when we compare a model with test data of an impostor user. The trust will drop (in this example) 5 times below the lockout threshold (Tlockout marked with a red line) within 100 user P5actions. The value of ANIA in this example equals 1 i=1 Ni . We can calculate ANGA in the same way, if 5 the genuine user is locked out based on his own test data. Our goal is obviously to have ANGA as high as possible, while at the same time the ANIA value must be as low as possible. The last is obviously to assure that an impostor user can do as little harm as possible, hence he/she must be detected as quick as possible. In our analysis, whenever a user is locked out, we reset the trust value to 100 to simulate a new session starting after the set of actions that lead to this lockout. In Figure 6, we can clearly see that the trust is set back 5 times to 100.
Figure 4. Score sc vs. ∆T rust (sc) from Equation 1 for different parameters.
T rust in the trust model (see Section 4.1). Finally, the trust value T rust is used in the decision module, to determine if the user will be locked out or can continue to use the device. This decision is made based on the current trust value and the lockout threshold (Tlockout ). For each action performed by the current user, the system calculates the score for that action (see for details the subsections in Section 3.2) and used that to calculate the change in trust according to Equation 2. Parameters A, B, C, and D in Equation 2 dependent on the user’s behaviour and are optimized according to that. In our experiment, we used linear search to optimize the parameters.
4.3.1
FNMR / FMR to ANGA / ANIA Conversion
Testing Pipeline Static Login
In this section, we show how, for a PA system, we can express FNMR and FMR in terms of ANGA and ANIA. Assume FNMR equals p and the system operates on chunks of m actions. The genuine user can always do m actions and with probability (1 − p) he can continue and do m more actions. After that, again with probability (1 − p), he can do m more actions, etc. So in total we find:
Continue
Lock out
Template Creation Pipeline
Swipe Feature Extraction Decision Module
Build Classifier Models
AN GA (1 − p) × m...
=
m + (1 − p) × m + (1 − p)2 × m +
So, AN GA
=
m m = 1 − (1 − p) p
3
Matching Module
Trust Model
Store Profiles
Figure 5. Block Diagram of the proposed system.
Similarly if FMR is p, then the imposter user can always do m actions and with the probability of p he can continue and do m more actions. After that again with probability p he can do m more actions, etc. So in total we find:
4.3. Performance Measure In the testing phase will we measure the performance of the system in terms of Average Number of Genuine Actions (ANGA) and Average Number of Impostor Actions (ANIA) [12]. The details explanation of the performed actions is
462
AN IA
=
So, AN IA
=
m + p × m + p2 × m + p3 × m... m 1−p
case indeed genuine users are locked out by the system. If the genuine users are not locked out, then we actually cannot calculate ANGA. The column ANIA will display the Average Number of Impostor Actions, and is based on all impostors that are detected. The actions of the impostors that are not detected are not used in this calculation, but the number of impostors that is not detected is given in the column # Imp. ND. This number should be seen in relation to the number of users in that particular category. For example, in the Set-1 ’+ / -’ category described in Table 1, we see that # Users equals 3, i.e. there are 3 × 70 = 210 impostor test sets, and only 4 imposters within these 210 impostors are not found by the system as being an impostor.
For example, Frank et al. [8] got an EER of 3% with chunks of 12 actions. So, p = 0.03 and m = 12; so AN GA = 12 12 0.03 = 400 and AN IA = 1−0.03 = 12. It is clear that an impostor can do at least m actions in a PA system because such a system checks the identity of the user for the first time after m actions.
5. Result Analysis In this section, we analyse the results that we obtained from our performance analysis. We divide our analysis into three major parts based on the verification process (see Section 3.1). As mentioned before, in this research the total number of data sets of genuine users is 71 and hence, the total number of data sets of impostor users is 4970 (71 × 70). We report the results from a one-hold-out cross validation test in terms of ANIA and ANGA along with the total number of impostors not detected for different lockout threshold (Tlockout ). Also, we report the results with the user specific lockout threshold (Tus ) where, the threshold for lockout will satisfy 50 ≤ Tus < min(T rustgenuine ). Besides reporting the performance in terms of ANIA and ANGA and in terms of the 4 categories described below, will we also report the results in terms of FMR and FNMR. We do realize that this is a slight abuse of terminology in the context of continuous authentication with our analysis methods, but we decided to do so to clarify the results in known terminology. Interpretation of the tables: When we present the results from our analysis, the results are shown for 4 possible categories. The categories are divided based on genuine user lockout (+ if the genuine user is not locked out and − in case of lock out) and non-detection of impostor users (+ if an impostor user is locked out and − otherwise). Each of the 71 users can thus be classified of 4 categories:
5.1. Result Table 1 shows the optimal result we got from this analysis for VP-1. The table is divided into two parts, based on the dataset used (i.e. Set-1 and Set-2). For Set-1 In total 68 users qualify for the best category for the user specific lockout threshold; whereas for the fixed threshold, this number drops to 63. We can observe from the table that if we go from a user specific lockout threshold (Tus ) to fixed lockout threshold (Tlockout = 90) the results are getting worse. For the fixed lockout threshold, the number of best performing users are decreasing, and the numbers for Positive vs. Negative are increasing. We also see that for Set-2 all the 51 users satisfied the best case category for the user specific lockout threshold. Table 2 displays the optimal result from the analysis for VP-2. We can clearly observe that all the 51 users satisfied the best case category for the user specific lockout threshold scheme on Set-2, but the ANIA increases from 5 for VP-1 to 6 for VP-2. Finally Table 3 shows the optimal result we got from this analysis for VP-3. It is not surprising that from Tables 1 to 3 we consistently see that the personal threshold performs better than the fixed system threshold. We first applied the methods proposed by Mondal and Bours [12] for VP-1 on Set-1 (i.e. Static Trust Model with Support Vector Machine as a classifier) and obtained an ANIA of 7 for only 22 users in the best category when using a user specific lockout threshold. Table 4 shows the result obtained from this analysis. We observe the significant improvement of the results when in this research by comparing the result in Tables 1 and 4.
• All Positive (+ / +) : This is the best case category. In this category, the genuine user is never locked out, and all the 70 impostors are detected as impostors. • Positive vs. Negative (+ / -) : In this category, the genuine user is not locked out but some impostors are not detected by the system. • Negative vs. Positive (- / +) : In this category, the genuine user is locked out by the system, but on the other hand are all impostors detected. • All Negative (- / -) : This is the worst case category. In this category, the genuine user is locked out by the system and also, some of the impostors are not detected.
Table 4. Results for VP-1 on Set-1 by using analysis method from [12].
Categories +/+ +/-/+ -/-
The column # Users shows how many users fall within each of the 4 categories (i.e. the values sum up to 71 for Set-1 and 51 for Set-2). In the column ANGA a value will indicate the Average Number of Genuine Actions in
463
# User 22 47
ANGA
2
113
ANIA 7 37
# Imp. ND
117
28
269
Table 1. Results for VP-1 with the analysis method.
Tlockout
Categories +/+ +/-/+ -/+/+ +/-/+ -/-
Tus
90
# User 68 3
ANGA
63 8
Set-1 ANIA 4 14
# Imp. ND
# User 51
ANGA
Set-2 ANIA 5
# Imp. ND
4
14 25
20
47 4
19 37
5
Table 2. Results for VP-2 with the analysis method.
Tlockout
Tus
90
Categories +/+ +/-/+ -/+/+ +/-/+ -/-
# User 66 5
ANGA
56 15
Set-1 ANIA 4 15
# Imp. ND
15 22
27
# Imp. ND
48 3
19 36
3
5.2. Comparison with Previous Research Due to its novelty, we have found few research which have addressed the continuous authentication by using mobile swipe gesture [7, 8, 15]. Table 6, shows the previous research results in terms of ANIA/ANGA by using the conversion technique describe in section 4.3.1. We can clearly see that our methods outperform these researches. The database we used is also large when compared to these three researches which provides statistical significance of this research. The major limitation of the state-of-the-art research is that they use fixed chunks of data (i.e. m actions) for analysis. An impostor can perform m actions before his identity is checked, even if a 0% EER rate is achieved. In fact, this is no longer CA, but at best periodic authentication. This limitation is mitigated by our proposed scheme.
Table 5. Results in terms of (FNMR, FMR).
VP-2 (0%, 0.2%) (0%, 0%)
Set-2 ANIA 6
Our major focus in this research was to develop a proper CA system, which can react every action performed by the user. A change of the pre-processing can influence the results (i.e. a different feature extraction process, a different feature selection techniques or the choice of classifiers). The goal in [1] was user identification and the authors showed that could reach a 95% accuracy when using chunk of 10 actions.
We report here the FNMR and FMR values for all the tests done in previous section. We will restrict ourselves to only the optimal settings, i.e. the user dependent threshold Tus . For example we see in Table 1, in that case none of the genuine user is locked out and that 4 impostor users are not detected (category +/-). This implies that F N M R = 0% and F M R = 4/4970 = 0.08%. All the results are presented in Table 5. In this table are the verification processes by the columns and the rows represent the dataset (i.e. Set-1 and Set-2).
VP-1 (0%, 0.08%) (0%, 0%)
ANGA
10
We also report the overall system performance in terms of FMR and FNMR, although we are aware that this is a slight abuse of terminology in the context of continuous authentication with our analysis methods. In this case we consider FMR as the probability that an impostor user is not detected when his test data is compared to the classification model of a genuine user. Each impostor data was tested against 71 genuine users for Set-1 and 51 for Set-2, which means that the total number of impostor tests equals 71×70 = 4970 for Set-1 and 51×50 = 2550 for Set-2. Similarly we also define the FNMR here as the probability that a genuine user is falsely locked out by the system.
Data Set Set-1 Set-2
# User 51
VP-3 (0%, 0.06%) (0%, 0.04%)
464
Table 3. Results for VP-3 with the analysis method.
Tlockout
Categories +/+ +/-/+ -/+/+ +/-/+ -/-
Tus
90
# User 68 3
ANGA
Set-1 ANIA 4 10
57 14
# Imp. ND
14 19
Table 6. Previous research results with our conversion method. Ref [8] [15] [7]
# Users 41 30 23
FNMR 3% 2.62% 9%
FMR 3% 2.62% 7%
Blocksize 12 6 8
ANGA 400 229 89
ANIA 12 6 9
[6]
[7]
6. Conclusion Our analysis was extensive in the sense that we applied three different verification processes and all different combinations of the settings with two separate sets of data. Although we applied the analysis in this research to a dataset with continuous swipe gesture data, are the techniques general enough that they can also be applied to, for example, keystroke dynamics data or any other biometric data that can be used for continuous authentication on mobile devices. We have shown that our results improve significantly over the previously known performance results, even though it is hard to compare the results in a straightforward manner. In the future we intend to perform a context independent long term experiment for continuous authentication to provide a deployable security solution.
[8]
[9]
[10]
References
[11]
[1] M. Antal, L. Z. Szabo, and Z. Bokor. Identity information revealed from mobile touch gestures. Studia Universitatis Babes-Bolyai, Informatica, LIX:1–14, 2014. [2] D. Ballabio and M. Vasighi. A matlab toolbox for self organizing maps and supervised neural network learning strategies. Chemometrics and Intelligent Laboratory Systems, 118(0):24 – 32, 2012. [3] P. Bours. Continuous keystroke dynamics: A different perspective towards biometric evaluation. Information Security Technical Report, 17:36–43, 2012. [4] Z. Cai, C. Shen, M. Wang, Y. Song, and J. Wang. Mobile authentication through touch-behavior features. In Biometric Recognition, volume 8232 of Lecture Notes in Computer Science, pages 386–393. Springer, 2013. [5] A. De Luca, A. Hang, F. Brudy, C. Lindner, and H. Hussmann. Touch me once and i know it’s you!: Implicit authentication based on touch screen patterns. In SIGCHI Con-
[12]
[13]
[14]
[15]
465
3
# User 50 1
22
49 2
ANGA
Set-2 ANIA 5 27
17 40
# Imp. ND 1
4
ference on Human Factors in Computing Systems, CHI ’12, pages 987–996. ACM, 2012. T. Feng, Z. Liu, K.-A. Kwon, W. Shi, B. Carbunar, Y. Jiang, and N. Nguyen. Continuous mobile authentication using touchscreen gestures. In IEEE Conference on Technologies for Homeland Security (HST’12), pages 451–456, Nov 2012. T. Feng, J. Yang, Z. Yan, E. M. Tapia, and W. Shi. Tips: Context-aware implicit user identification using touch screen in uncontrolled environments. In 15th Workshop on Mobile Computing Systems and Applications (HotMobile ’14), pages 9:1–9:6. ACM, 2014. M. Frank, R. Biedert, E. Ma, I. Martinovic, and D. Song. Touchalytics: On the applicability of touchscreen input as a behavioral biometric for continuous authentication. IEEE Transactions on Information Forensics and Security, 8(1):136–148, Jan 2013. J. Kittler, M. Hatef, R. P. W. Duin, and J. Matas. On combining classifiers. IEEE Trans. on Pattern Analysis and Machine Intelligence, 20(3):226–239, 1998. C. Lazar, J. Taminau, S. Meganck, D. Steenhoff, A. Coletta, C. Molter, V. de Schaetzen, R. Duque, H. Bersini, and A. Nowe. A survey on filter techniques for feature selection in gene expression microarray analysis. IEEE/ACM Trans. on Computational Biology and Bioinformatics, 9(4):1106– 1119, 2012. Y. Meng, D. S. Wong, and L.-F. Kwok. Design of touch dynamics based user authentication with an adaptive mechanism on mobile phones. In 29th Annual ACM Symposium on Applied Computing, SAC ’14, pages 1680–1687. ACM, 2014. S. Mondal and P. Bours. Continuous authentication using mouse dynamics. In Int. Conf. of the Biometrics Special Interest Group (BIOSIG’13), pages 1–12, Sept 2013. S. Mondal and P. Bours. A computational approach to the continuous authentication biometric system. Information Sciences, 304:28 – 53, 2015. I. T. Nabney. Netlab: Algorithms for Pattern Recognition, volume XVIII of Advances in Computer Vision and Pattern Recognition. Springer, 2002. X. Zhao, T. Feng, and W. Shi. Continuous mobile authentication using a novel graphic touch gesture feature. In 2013 IEEE Int. Conf. on Biometrics: Theory, Applications and Systems (BTAS), pages 1–6, Sept 2013.
