No abstract

No abstract

Due to the widespread use of cloud systems nowadays, strong authentication mechanisms are needed in order to secure personal files. Out of diverse ways to improve secure authentication, keystroke dynamics is of interest because it is inexpensive and needs no extra hardware systems. Furthermore, authentication systems with proper machine learning algorithms can acquire humans' typical typing behaviors from their keystroke dynamics, which entails difficulty for imposters to imitate a legitimate user's typing behavior. In this paper, we introduce sequence alignment algorithm with dynamic interval features (SADI) from keystrokes to model behavior-based authentication system. An interval feature is basically the length of each attribute label and it is used in a sequence alignment algorithm to divide every attribute into sections. However, dynamic interval features, proposed in this research, are similar to interval feature but they divide every attribute into different number of sections. Dynamic interval features are chosen to maximize comparison capability of similarity measures from keystroke data. Experimental results on the CMU public benchmark dataset indicate that the proposed SADI is comparable to and sometimes outperforms other published methods.

Keystroke dynamics based authentication is one of the prevention mechanisms used to protect one’s account from criminals’ illegal access. In this authentication mechanism, keystroke dynamics are used to capture patterns in a user typing behavior. Sequence alignment is shown to be one of effective algorithms for keystroke dynamics based authentication, by comparing the sequences of keystroke data to detect imposter’s anomalous sequences. In previous research, static divisor has been used for sequence generation from the keystroke data, which is a number used to divide a time difference of keystroke data into an equal-length subinterval. After the division, the subintervals are mapped to alphabet letters to form sequences. One major drawback of this static divisor is that the amount of data for this subinterval generation is often insufficient, which leads to premature termination of subinterval generation and consequently causes inaccurate sequence alignment. To alleviate this problem, we introduce sequence alignment of dynamic divisor (SADD) in this paper. In SADD, we use mean of Horner’s rule technique to generate dynamic divisors and apply them to produce the subintervals with different length. The comparative experimental results with SADD and other existing algorithms indicate that SADD is usually comparable to and often outperforms other existing algorithms.

Adversarial examples have proved efficacious in fooling deep neural networks recently. Many researchers have studied this issue of adversarial examples by evaluating neural networks against their attack techniques and increasing the robustness of neural networks with their defense techniques. To the best of our knowledge, adversarial training is one of the most effective defense techniques against the adversarial examples. However, the method is not able to cope with new attacks because it requires attack techniques in the training phase. In this paper, we propose a novel defense technique, Attack-Less Adversarial Training (ALAT) method, which is independent from any attack techniques, thereby is useful in preventing future attacks. Specifically, ALAT regenerates every pixel of an image into different pixel value, which commonly eliminates the majority of the adversarial noises in the adversarial example. This pixel regeneration is useful in defense because the adversarial noises are the core problem that make the neural networks produce high misclassification rate. Our experiment results with several benchmark datasets show that our method not only relieves over-fitting issue during the training of neural networks with a large number of epochs, but also boosts the robustness of the neural network.