Razlike

Slijede razlike između dviju inačica stranice.

--- racfor_wiki:primjene_strojnog_ucenja_u_cyber_sigurnosti [2021/01/17 13:31]
mpuhalovic [Breaking Human Interaction Proofs (HIPs)]
+++ racfor_wiki:primjene_strojnog_ucenja_u_cyber_sigurnosti [2024/12/05 12:24] (trenutno)
@@ Redak 154: / Redak 154: @@
 ===== Breaking Human Interaction Proofs (HIPs) =====
-Researchers [5] proposed a machine learning approach for breaking Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs) and Human Interaction Proofs (HIPs). The proposed approach is aimed at locating the characters (segmentation step) and employing a neural network for character recognition.
+Researchers [5] proposed a machine learning approach for breaking Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs) and Human Interaction Proofs (HIPs). The proposed approach is aimed at locating the characters (segmentation step) and employing a neural network for character recognition (recognition step).
-Each experiment was split into two parts:
+So, each experiment was split into two parts:
   * segmentation
   * recognition
-Segmentation part was relatively difficult for the following reasons:
+The segmentation part was relatively difficult for the following reasons:
   * it is computationally expensive
   * complex segmentation function
@@ Redak 167: / Redak 167: @@
 Their method for breaking HIPs is to write a custom algorithm to locate the characters, and then use machine learning for recognition. Surprisingly, segmentation was simple for many HIPs which made the process of breaking the HIP particularly easy. Once the segmentation problem is solved, solving the HIP becomes a pure recognition problem, and it can trivially be solved using machine learning. Their recognition engine is based on a neural network.
-On the segmentation stage, different computer vision techniques like converting to grayscale, thresholding to black and white, dilating and eroding, and selecting large connected components (CCs) with sizes close to HIP char sizes were applied. An example of the segmentation process is shown in Image x. The first image shows the original HIP, the second image shows the processed HIP, and the third image shows HIP with segmented characters.
+On the segmentation stage, different computer vision techniques like converting to grayscale, thresholding to black and white, dilating and eroding, and selecting large connected components (CCs) with sizes close to HIP char sizes were applied. An example of the segmentation process is shown in Image 2. The first image shows the original HIP, the second image shows the processed HIP, and the third image shows HIP with segmented characters.
+Image 2 [5]:
-IMAGE:
 {{:racfor_wiki:captcha_segmentation.png?400|}}
-The first 3 segmented images from the previous example, which are fed to the neural network, are shown in Image x.
+The first 3 segmented images from the previous example, which are fed to the neural network, are shown in Image 3.
+Image 3 [5]:
-IMAGE:
 {{:racfor_wiki:captcha_segmented.png?400|}}
-Six experiments were conducted with EZ-Gimpy/Yahoo, Yahoo v2, mailblocks, register, ticketmaster, and Google HIPs. The segmentation success rates and recognition success rates of each experiment are shown in Table x.
+Six experiments were conducted with EZ-Gimpy/Yahoo, Yahoo v2, mailblocks, register, ticketmaster, and Google HIPs. The segmentation success rates and recognition success rates of each experiment are shown in Table 6.
-Table 1:
+Table 6 [5]:
 |  \\ HIP   \\ |  \\ Segmentation success rate   \\ |  \\ Recognition success rate (after segmentation)   \\ |  \\ Total   \\ |
 |  \\ Mailblocks \\ |  \\  88.8 %  \\ |  \\ 95.9 %  \\ | \\ 66.2 %  \\ |
@@ Redak 198: / Redak 200: @@
   * Attacks on availability - cause so many classification errors that the system becomes effectively unusable
   * Exploratory attacks - exploiting the existing vulnerabilities
-  * Targeted attacks directed to a certain input;
+  * Targeted attacks - directed to a certain input
-  * Indiscriminate attacks - in which inputs fail.
+  * Indiscriminate attacks - causes all inputs to fail
-The researchers [] proposed the Reject On Negative Impact (RONI) defense which ignores all the training data points that have a substantial negative impact on the classification accuracy.
-RONI defense system consists of two classifiers. One classifier is trained using the base training set and the other is trained with the base set and potentially malicious data. If the errors of those two classifiers differ significantly from each other the data is labeled as malicious.
-RONI defense defends against exploratory and causative attacks. For defending against exploratory attacks, in which an attacker can create an evaluation distribution that the learner predicts poorly, the defender can limit the access to the training procedure and data, making it harder for an attacker to apply reverse engineering. For defending against the causative attacks, in which an attacker can manipulate both training and evaluation distributions, the defender can employ previously described defense using two classifiers.
+The researchers [10] proposed a defense against exploratory and causative attacks.
+For defending against exploratory attacks, in which an attacker can create an evaluation distribution that the learner predicts poorly, the defender can limit the access to the training procedure and data, making it harder for an attacker to apply reverse engineering.
+For defending against the causative attacks, in which an attacker can manipulate both training and evaluation distributions, the defender can employ Reject On Negative Impact (RONI) defense. RONI defense ignores all the training data points that have a substantial negative impact on classification accuracy. RONI defense consists of two classifiers. One classifier is trained using the base training set and the other is trained with the base set and potentially malicious data. If the errors of those two classifiers differ significantly from each other the data is labeled as malicious.
 ===== Conclusion =====
-Machine learning is a powerful and adaptive tool that enabled tackling problems that so far required humans. It also enabled the automation of threat recognition tasks.
+Machine learning is a powerful and adaptive tool that enabled tackling problems that so far required humans. It also enabled the automation of threat recognition tasks. In this paper, multiple applications of machine learning in cybersecurity were shown. Most of the problems were solved using supervised learning and classification since their required classifying input into safe or malicious categories. For classification tasks, researchers tested multiple classifiers, each with its own pros and cons, and they chose what they considered the best ones for the task at hand.
-===== Literatura =====
+===== Literature =====
-[1] [[https://www.researchgate.net/publication/283083699_Applications_of_Machine_Learning_in_Cyber_Security|Ford, V., and Siraj A. Applications of Machine Learning in Cyber Security. Computer Science Department, Tennessee Tech University, 2014., accessed on January 2020.]]
+[1] [[https://www.researchgate.net/publication/283083699_Applications_of_Machine_Learning_in_Cyber_Security|Ford, V., and Siraj, A. Applications of Machine Learning in Cyber Security. Computer Science Department, Tennessee Tech University, 2014. Accessed in January 2021.]]
-[2] [[https://www.nccgroup.trust/globalassets/our-research/uk/whitepapers/2017/rise-of-the-machines-preliminaries-wp-new-template-final_web.pdf|Matt Lewis. Rise of the machines: Machine Learning & its cyber security applications. NCC Group, 2017., accessed on January 2020.]]
+[2] [[https://www.nccgroup.trust/globalassets/our-research/uk/whitepapers/2017/rise-of-the-machines-preliminaries-wp-new-template-final_web.pdf|Matt Lewis. Rise of the machines: Machine Learning & its cyber security applications. NCC Group, 2017. Accessed in January 2021.]]
-[3] [[https://resources.sei.cmu.edu/library/asset-view.cfm?assetid=633583|Spring, J., Fallon, J., Galyardt, A., Horneman, A., Metcalf, L. B., and Stoner, E. Machine Learning in Cybersecurity: A Guide. Software Engineering Institute, 2019., accessed on January 2020.]]
+[3] [[https://resources.sei.cmu.edu/library/asset-view.cfm?assetid=633583|Spring, J., Fallon, J., Galyardt, A., Horneman, A., Metcalf, L. B., and Stoner, E. Machine Learning in Cybersecurity: A Guide. Software Engineering Institute, 2019. Accessed in January 2021.]]
+[4] [[https://arxiv.org/abs/1906.05799|Nguyen, T. T. and Reddi, V. J. Deep Reinforcement Learning for Cyber Security. 2020. Accessed in January 2021.]]
-[4] https://arxiv.org/abs/1906.05799
+[5] [[https://papers.nips.cc/paper/2004/file/283085d30e10513624c8cece7993f4de-Paper.pdf|Chellapilla, K. and Simard, P. Y. Using Machine Learning to Break Visual Human Interaction Proofs (HIPs). Microsoft Research. Accessed in January 2021.]]
-[5] https://papers.nips.cc/paper/2004/file/283085d30e10513624c8cece7993f4de-Paper.pdf
+[6] [[https://eprints.whiterose.ac.uk/128366/1/MalwareAnalysis.pdf|Milošević, N., Dehghantanha, A. and Choo, K.-K.R. Machine learning aided malware classification of Android applications. 2017. Accessed in January 2021.]]
-[6]https://eprints.whiterose.ac.uk/128366/1/MalwareAnalysis.pdf
+[7][[https://www.researchgate.net/publication/216864662_A_machine_learning_approach_to_keystroke_dynamics_based_user_authentication|Revett, K., Gorunescu, F., Gorunescu, M. and Ene, M. A machine learning approach to keystroke dynamics based user authentication. International Journal of Electronic Security and Digital Forensics. 2007. Accessed in January 2021.]]
-[7] https://www.researchgate.net/publication/216864662_A_machine_learning_approach_to_keystroke_dynamics_based_user_authentication
+[8][[https://www.usenix.org/legacy/events/sec08/tech/full_papers/gu/gu_html/index.html|Gu, G., Perdisci, R., Zhang, J., and Lee, W. BotMiner: Clustering Analysis of Network Traffic for Protocol- and Structure-Independent Botnet Detection. College of Computing, Georgia Institute of Technology. Accessed in January 2021.]]
-[8] https://www.usenix.org/legacy/events/sec08/tech/full_papers/gu/gu_html/index.html
+[9][[http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.114.1242&rep=rep1&type=pdf|Abu-Nimeh, S., Nappa, D., Wang, X. and Nair, S. A Comparison of Machine Learning Techniques for Phishing Detection. SMU HACNet Lab, Southern Methodist University. 2007. Accessed in January 2021.]]
-[9] http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.114.1242&rep=rep1&type=pdf
+[10][[https://people.eecs.berkeley.edu/~adj/publications/paper-files/SecML-MLJ2010.pdf|Barreno, M., Nelson, B. Joseph, A. D., Tygar, J.D. The security of machine learning. Computer Science Division, University of California, Berkeley. 2008. Accessed in January 2021.]]

racfor_wiki/primjene_strojnog_ucenja_u_cyber_sigurnosti.1610890311.txt.gz · Zadnja izmjena: 2024/12/05 12:23 (vanjsko uređivanje)