בפרק זה, נדבר על Adversarial Attacks, על איך מייצרים Adversarial Examples בשיטת FGSM, על התקפות White or Black box models ונזכיר Certifiable Robustness.
<ul>
<li><ul>
<li style="font-weight:400;"><a href="https://arxiv.org/pdf/1412.6572.pdf" target="_blank" rel="noreferrer noopener">FGSM</a></li>
<li style="font-weight:400;"><a href="https://www.researchgate.net/publication/327074374_A_Survey_of_Adversarial_Machine_Learning_in_Cyber_Warfare" target="_blank" rel="noreferrer noopener">A Survey of Adversarial Machine Learning in Cyber Warfare</a></li>
<li style="font-weight:400;"><a href="https://arxiv.org/pdf/1707.03501.pdf" target="_blank" rel="noreferrer noopener">no need to worry about adversarial examples in object detection in autonomous vehicles</a></li>
</ul></li>
</ul>

בפרק זה, נדבר על Adversarial Attacks, על איך מייצרים Adversarial Examples בשיטת FGSM, על התקפות White or Black box models ונזכיר Certifiable Robustness. FGSM A Survey of Adversarial Machine Learning in Cyber Warfare no need to worry about adversarial examples in object detection in autonomous vehicles

בפרק זה,&nbsp;נדבר על Adversarial Attacks, על איך מייצרים Adversarial Examples בשיטת FGSM, על התקפות White or Black box models ונזכיר Certifiable Robustness.
<ul>
<li><ul>
<li><a href="https://arxiv.org/pdf/1412.6572.pdf" rel="noopener noreferrer">FGSM</a></li>
<li><a href="https://www.researchgate.net/publication/327074374_A_Survey_of_Adversarial_Machine_Learning_in_Cyber_Warfare" rel="noopener noreferrer">A Survey of Adversarial Machine Learning in Cyber Warfare</a></li>
<li><a href="https://arxiv.org/pdf/1707.03501.pdf" rel="noopener noreferrer">no need to worry about adversarial examples in object detection in autonomous vehicles</a></li>
</ul></li>
</ul>

Share Episode 9: Adversarial Training - איך לבלבל מודלים?

Sign up to save your podcasts

Episode 9: Adversarial Training - איך לבלבל מודלים?

Episode 9: Adversarial Training - איך לבלבל מודלים?