Abstract
Artificial Intelligence (AI) in general and Machine Learning (ML) in particular, have received much attention in recent years also thanks to current advancements in computational infrastructures. One prominent example application of ML is given by image recognition services that allow to recognize characteristics in images and classify them accordingly. One question that arises, also in light of current debates that are fueled with emotions rather than evidence, is to which extent such ML services can already pass image-based Turing Tests. In other words, can ML services imitate human (cognitive and creative) tasks to an extent that their behavior remains indistinguishable from human behavior? If so, what does this mean from a security perspective? In this paper, we evaluate a number of publicly available ML services for the degree to which they can be used to pass image-based Turing Tests. We do so by applying selected ML services to 10,500 randomly collected captchas including approximately 100,000 images. We further investigate the degree to which captcha solving can become an automated procedure. Our results strengthen our confidence in that today’s available and ready-to-use ML services can indeed be used to pass image-based Turing Tests, rising new questions on the security of systems that rely on this image-based technology as a security measure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amazon Rekognition. Deep Learning-Based Image Recognition—Search, Verify, and Organize Millions of Images. https://aws.amazon.com/rekognition/
Baecher, P., Büscher, N., Fischlin, M., Milde, B.: Breaking reCAPTCHA: a holistic approach via shape recognition. In Future Challenges in Security and Privacy for Academia and Industry (2011)
Bursztein, E., Aigrain, J., Moscicki, A., Mitchell, J.C.: The end is nigh: generic solving of text-based CAPTCHAs. In USENIX Workshop on Offensive Technologies (WOOT) (2014)
Bursztein, E., Beauxis, R., Paskov, H., Perito, D., Fabry, C., Mitchell, J.: The failure of noise-based non-continuous audio captchas. In: IEEE Symposium on Security and Privacy (2011)
Chellapilla, K., Simard, P.Y.: Using machine learning to break visual human interaction proofs (HIPs). In: Advances in Neural Information Processing Systems (2005)
Chollet, F.: Deep Learning With Python. Manning, Shelter Island (2017)
Clarifai. Artificial Intelligence With a Vision. https://clarifai.com/
Cliq Orange. https://www.cliqorange.com/
Cloudsight. Visual Cognition—High Quality Understanding of Images Within Seconds. https://cloudsight.ai/
Collobert, R., Weston, J.: A unified architecture for natural language processing: deep neural networks with multitask learning. In: International Conference on Machine Learning (2008)
Cruz-Perez, C., Starostenko, O., Uceda-Ponga, F., Alarcon-Aquino, V., Reyes-Cabrera, L.: Breaking reCAPTCHAs with unpredictable collapse: heuristic character segmentation and recognition. In: Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Olvera López, J.A., Boyer, K.L. (eds.) MCPR 2012. LNCS, vol. 7329, pp. 155–165. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31149-9_16
Deng, L., Yu, D.: Deep learning: methods and applications. Found. Trends Sig. Process. 7(3–4), 197–387 (2014)
Google. reCAPTCHA: Protect Your Site From Spam and Abuse. https://developers.google.com/recaptcha/
Google Cloud Vision. Derive Insight From Images With Our Powerful Cloud Vision API (2017). https://cloud.google.com/vision/
Goswami, G., Powell, B.M., Vatsa, M., Singh, R., Noore, A.: FaceDCAPTCHA: face detection based color image CAPTCHA. Future Gener. Comput. Syst. 31, 59–68 (2014)
de Gyor, H.: Keywording Now: Practical Advice on Using Image Recognition and Keywording Services. Another DAM Consultancy (2017)
Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Sig. Process. Mag. 29, 82–97 (2012)
Hive.AI. Powering Artificial Intelligence. https://thehive.ai/
IBM. Watson Visual Recognition (2017). https://www.ibm.com/watson/services/visual-recognition/
ICrimson Hexagon. https://www.crimsonhexagon.com/
Imagga. Build Your Apps on Top of an Advanced Image Tagging Technology. https://imagga.com/
JASTEC: A Pioneer of Image Recognition. http://www.jastec.fr/
Kolosnjaji, B., Eraisha, G., Webster, G., Zarras, A., Eckert, C.: Empowering convolutional networks for malware classification and analysis. In: International Joint Conference on Neural Networks (IJCNN), pp. 3838–3845. IEEE (2017)
Kolosnjaji, B., Zarras, A., Webster, G., Eckert, C.: Deep learning for classification of malware system call sequences. In: Kang, B.H., Bai, Q. (eds.) AI 2016. LNCS (LNAI), vol. 9992, pp. 137–149. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50127-7_11
Kopp, M., Pistora, M., Holena, M.: How to mimic humans, guide for computers. In: ITAT (2016)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Meutzner, H., Nguyen, V.-H., Holz, T., Kolossa, D.: Using automatic speech recognition for attacking acoustic CAPTCHAs: the trade-off between usability and security. In: Annual Computer Security Applications Conference (ACSAC) (2014)
Microsoft. Computer Vision API. https://azure.microsoft.com/en-us/services/cognitive-services/computer-vision/
NY Times. Please Prove You’re Not a Robot. https://www.nytimes.com/2017/07/15/opinion/sunday/please-prove-youre-not-a-robot.html
Reshef, E., Raanan, G., Solan, E.: Method and system for discriminating a human action from a computerized action (2004)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
Saltlab World. Image & Object Recognition System & API. http://saltlabworld.com/
Scale. Image Annotation API. https://www.scaleapi.com/image-annotation
Sivakorn, S., Polakis, I., Keromytis, A.D.: I am robot: (deep) learning to break semantic image CAPTCHAs. In: IEEE European Symposium on Security and Privacy, EuroS&P (2016)
Turing, A.M.: Computing machinery and intelligence. Mind 59(236), 433–460 (1950)
Vize.ai. Custom Image Recognition API. https://vize.ai/
von Ahn, L., Blum, M., Hopper, N.J., Langford, J.: CAPTCHA: using hard AI problems for security. In: Biham, E. (ed.) EUROCRYPT 2003. LNCS, vol. 2656, pp. 294–311. Springer, Heidelberg (2003). https://doi.org/10.1007/3-540-39200-9_18
Xu, Y., Reynaga, G., Chiasson, S., Frahm, J.-M., Monrose, F., van Oorschot, P.C.: Security and usability challenges of moving-object CAPTCHAs: decoding codewords in motion. In: USENIX Security Symposium (2012)
Yan, J., El Ahmad, A.S.: Breaking visual captchas with Naive pattern recognition algorithms. In: Annual Computer Security Applications Conference (ACSAC) (2007)
Yan, J., El Ahmad, A.S.: A low-cost attack on a microsoft CAPTCHA. In: ACM Conference on Computer and Communications Security (CCS) (2008)
Acknowledgments
This work was supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 833115 (PREVISION).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zarras, A., Gerostathopoulos, I., Fernández, D.M. (2019). Can Today’s Machine Learning Pass Image-Based Turing Tests?. In: Lin, Z., Papamanthou, C., Polychronakis, M. (eds) Information Security. ISC 2019. Lecture Notes in Computer Science(), vol 11723. Springer, Cham. https://doi.org/10.1007/978-3-030-30215-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-30215-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30214-6
Online ISBN: 978-3-030-30215-3
eBook Packages: Computer ScienceComputer Science (R0)