PENGUJIAN KETAHANAN NEURAL NETWORK TERHADAP ONE PIXEL ATTACK (STUDI KASUS: MENGAMANKAN GAMBAR CAPTCHA DARI SERANGAN SIBER)

• MUHAMMAD DWISON ALIZAH
• 14002299

---

ABSTRAK

ABSTRAK

 

Nama               : Muhammad Dwison Alizah

NIM                : 14002299

Program Studi : Ilmu Komputer

Jenjang            : Program Magister (S2)

Konsentrasi     : Data Mining

Judul               : Pengujian Ketahanan Neural Network Terhadap One Pixel Attack

                          (Studi Kasus: Mengamankan Gambar Captcha dari Serangan

                          Siber)

 

Kebutuhan akan penggunaan website sangatlah tinggi. Hal ini memicu banyaknya serangan yang mungkin terjadi. Salah satu celah keamanan pada website adalah brute force attack. CAPTCHA merupakan solusi dari permasalahan tersebut. Akan tetapi, pemecahan CAPTCHA berbasis Neural Network telah berhasil diimplementasikan. Oleh karenanya, penelitian ini bermaksud untuk mengelabui Neural Network untuk mengamankan CAPTCHA dari serangan tersebut. Adversarial image adalah salah satu teknik yang dapat mengelabui Neural Network. Namun, penerapan adversarial image kurang efektif karena akan mempersulit pengguna dalam mengenali CAPTCHA. Perlu diterapkan sebuah metode untuk mengelabui Neural Network tanpa melakukan banyak perubahan. Pada penelitian ini, One Pixel Attack diterapkan terhadap CAPTCHA guna mengamankannya. CAPTCHA yang digunakan berasal dari sumber terbuka. Beberapa teknik eksplorasi dan modifikasi diterapkan pada CAPTCHA sebelum dilakukan learning menggunakan Neural Network. Performa dari One Pixel Attack sangat baik dalam menurunkan performa Neural Network. Ia mampu menurunkan performa Neural Network dari 97% ke 78% dan pada penerapan kedua mampu turun hingga 8%.

 

Kata kunci : CAPTCHA, Neural Network, One Pixel Attack

KATA KUNCI

Data Mining,Neural Network

---

DAFTAR PUSTAKA

DAFTAR PUSTAKA

 

[1]      N. N. Keumala, “Mempengaruhi Pelaporan Keuangan Perusahaan Melalui Website Perusahaan,” Skripsi, pp. 1–64, 2013.

[2]      The OWASP Foundation, “OWASP Top 10 - 2017: The Ten Most Critical Web Application Security Risks,” 2017 7th Int. Conf. Power Syst. ICPS 2017, 2018.

[3]      C. Paar and J. Pelzl, Understanding Cryptography. 2010.

[4]      L. Von Ahn, M. Blum, and J. Langford, “Telling humans and computers apart automatically,” Communications of the ACM. 2004.

[5]      M. Tang, H. Gao, Y. Zhang, Y. Liu, P. Zhang, and P. Wang, “Research on Deep Learning Techniques in Breaking Text-Based Captchas and Designing Image-Based Captcha,” IEEE Trans. Inf. Forensics Secur., vol. 13, no. 10, pp. 2522–2537, 2018.

[6]      G. Garg, C. Pollett, and S. J. Ca, “Neural Network CAPTCHA Crackers,” no. December, 2016.

[7]      D. Lin, F. Lin, Y. Lv, F. Cai, and D. Cao, “Chinese Character CAPTCHA Recognition and performance estimation via deep neural network,” Neurocomputing, 2018.

[8]      S. M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard, “DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016.

[9]      I. J. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and harnessing adversarial examples,” in 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 2015.

[10]    N. Papernot, P. Mcdaniel, S. Jha, M. Fredrikson, Z. B. Celik, and A. Swami, “The limitations of deep learning in adversarial settings,” in Proceedings - 2016 IEEE European Symposium on Security and Privacy, EURO S and P 2016, 2016.

[11]    J. Su, D. V. Vargas, and K. Sakurai, “One Pixel Attack for Fooling Deep Neural Networks,” IEEE Trans. Evol. Comput., 2019.

[12]    B. A. B. Ii, “Data Mining Data mining,” Min. Massive Datasets, vol. 2, no. January 2013, pp. 5–20, 2005.

[13]    J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques. 2012.

[14]    I. H. Witten, E. Frank, and M. a. Hall, Data Mining: Practical Machine Learning Tools and Techniques, Third Edition. 2011.

[15]    Iyer Aurobind Venkatkumar and Sanatkumar Jayantibhai Kondhol Shardaben, “Estudio comparativo de algoritmos de agrupamiento de minería de datos,” 2016.

[16]    P. A. Wardhani, Business Intelligence, Analytics, and Data Science: A Managerial Perspective, 4th ed., vol. 6. Pearson, 2015.

[17]    A. Azevedo and M. F. Santos, “KDD, semma and CRISP-DM: A parallel overview,” in MCCSIS’08 - IADIS Multi Conference on Computer Science and Information Systems; Proceedings of Informatics 2008 and Data Mining 2008, 2008.

[18]    J. J. Hopfield, “Neural networks and physical systems with emergent

collective computational abilities.,” Proc. Natl. Acad. Sci. U. S. A., 1982.

[19]    J. Schmidhuber, “Deep Learning in neural networks: An overview,” Neural Networks, vol. 61, pp. 85–117, 2015.

[20]    “ANN,” 2020. [Online]. Available: https://www.innoarchitech.com/blog/artificial-intelligence-deep-learning-neural-networks-explained.

[21]    S. Sharma, S. Sharma, and A. Athaiya, “Activation Functions in Neural Networks,” Int. J. Eng. Appl. Sci. Technol., vol. 04, no. 12, pp. 310–316, 2020.

[22]    N. Baba, “A new approach for finding the global minimum of error function of neural networks,” Neural Networks, vol. 2, no. 5, pp. 367–373, 1989.

[23]    L. Von Ahn, M. Blum, N. J. Hopper, and J. Langford, “CAPTCHA: Using hard AI problems for security,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 2003.

[24]    E. Bursztein, M. Martin, and J. C. Mitchell, “Text-based CAPTCHA strengths and weaknesses,” in Proceedings of the ACM Conference on Computer and Communications Security, 2011, pp. 125–137.

[25]    V. Singh and P. Pal, “Survey of different types of CAPTCHA,” Int. J. Comput. Sci. Inf. Technol., vol. 5, no. 2, pp. 2242–2245, 2014.

[26]    T. B. Brown, D. Mané, A. Roy, M. Abadi, and J. Gilmer, “Adversarial Patch,” no. Nips, 2017.

[27]    D. V. Vargas and J. Su, “Understanding the One-Pixel Attack: Propagation Maps and Locality Analysis,” pp. 2–11, 2019.

[28]    D. Kuhlman, “A Python Book: Beginning Python, Advanced Python, and Python Exercises,” A Python B., 2009.

[29]    “Website Python,” 2020. .

[30]    “Python OpenCV,” 2019. [Online]. Available: https://www.geeksforgeeks.org/python-opencv-cv2-copymakeborder-method/.

[31]    OpenCV, “otsu.” [Online]. Available: https://docs.opencv.org/master/d7/d4d/tutorial_py_thresholding.html.

[32]    Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, 1998.

[33]    “cnn.” missinglink.ai.

[34]    J. Jin, A. Dundar, and E. Culurciello, “R Obust C Onvolutional N Eural N Etworks,” pp. 1–8, 2016.