Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Intelligenza Artificiale e Sicurezza Informatica

62 views

Published on

Prof. Luigi V. Mancini
Dipartimento di Informatica
Sapienza Università di Roma

Published in: Education
  • Be the first to comment

  • Be the first to like this

Intelligenza Artificiale e Sicurezza Informatica

  1. 1. Intelligenza Artificiale nella PA: esperienze e prospettive Roma, 5 Novembre 2019 h. 9.00-13.30 organizzato e promosso da www.prsmonitor.euwww.di.uniroma1.itwww.miur.gov.it Intelligenza Artificiale e Sicurezza Informatica Prof. Luigi V. Mancini Dipartimento di Informatica Sapienza Università di Roma
  2. 2. organizzato e promosso da 2 Nominativo Speaker Ruolo - Organizzazione
  3. 3. organizzato e promosso da 3 Nominativo Speaker Ruolo - Organizzazione
  4. 4. organizzato e promosso da 4 Nominativo Speaker Ruolo - Organizzazione
  5. 5. https://www.di.uniroma1.it
  6. 6. Sapienza is among the Members of the Algorand Foundation university committee;
  7. 7. organizzato e promosso da 12 Nominativo Speaker Ruolo - Organizzazione Dijsktra Prize 2019 – Prof A. Panconesi
  8. 8. Success of Deep Learning • Branch of machine learning that makes use of neural networks, to find solutions for a variety of complex tasks either in supervised or unsupervised way - Areas used: - Computer vision - Image processing - Face recognition - Speech recognition - Text-to-speech systems - Natural language processing - Games... 13 image source: https://goo.gl/u26HM3 image source: https://goo.gl/xNwTVw image source: https://deepmind.com/research/alphago/
  9. 9. organizzato e promosso da 14 Nominativo Speaker Ruolo - Organizzazione Attacks Machine Learning to perform Attacks Deep Fakes and Social Bots
  10. 10. organizzato e promosso da 15 Nominativo Speaker Ruolo - Organizzazione DeepFakes
  11. 11. organizzato e promosso da 16 Nominativo Speaker Ruolo - Organizzazione Social engineering Companies are prey to increasingly sophisticated computer scams, carried out using social engineering, emails, etc. With deep fake, you could get to simulate a videoconference from the CEO of the company.
  12. 12. organizzato e promosso da 17 Nominativo Speaker Ruolo - Organizzazione The Building block of DeepFakes The Autoencoder
  13. 13. organizzato e promosso da 18 Nominativo Speaker Ruolo - Organizzazione How DeepFakes work? First phase
  14. 14. organizzato e promosso da 19 Nominativo Speaker Ruolo - Organizzazione Cont... 2nd phase
  15. 15. organizzato e promosso da 20 Nominativo Speaker Ruolo - Organizzazione Test di Turing A machine considered intelligent if it is indistinguishable from a human being.
  16. 16. organizzato e promosso da 21 Nominativo Speaker Ruolo - Organizzazione CAPTCHA examples
  17. 17. (1) (2)
  18. 18. CAPTCHA solving BOTS
  19. 19. organizzato e promosso da 25 Nominativo Speaker Ruolo - Organizzazione Agenda Attacks against Machine Learning
  20. 20. Trainset data poisoning
  21. 21. Adversarial examples
  22. 22. Cont...
  23. 23. Attacks on ML models 1) Hacking Smart Machines with Smarter Ones, 2011 by Mancini et al. 2) Model Inversion Attacks, 2015 by Fredrikson et al. 3) Membership Inference Attacks, 2017 by Shokri et al. 29
  24. 24. Facebook Day at Dipartimento di informatica
  25. 25. Where are now our students?
  26. 26. organizzato e promosso da 32 Nominativo Speaker Ruolo - Organizzazione Concluding Remarks Researchers are constantly engaged in exploring Machine Learning and the related Privacy and Security Issues. In order to find innovative and effective solutions, it is necessary to invest in research and not only in the market. Acquire Kow-how so we can always be a little ahead of the attackers. The Public Administration protects the interests of the community and cannot afford to lag behind the attackers.
  27. 27. organizzato e promosso da 33 Nominativo Speaker Ruolo - Organizzazione THANK YOU
  28. 28. G D 34 Discriminator D Eyewitness Generator G Police Sketch Artist Dataset “Real” Data Sample “Fake” Data Sample real sample fake sample GAN Architecture Generative Adversarial Network (GAN) basic architecture

×