Is there a coming phishpocalypse?
Generating (and detecting) phishing and spam emails with state-of-the-art language neural networks
Is there a coming phishpocalypse?
Deep language-based neural networks are surprisingly good at generating and detecting text of all forms. Some AI labs have been hesitant to release the details of their models for fear that they would be used to spread fake news, spam, and disinformation. What if they were used to generate phishing campaigns, for example?
This talk will dive into the details of how phishing and spam emails can be created with these novel text generation neural-networks. The talk will also explain how these kinds of emails can be identified and prevented.
Join this talk to learn:
- Background on neural networks in the security space
- A primer on text generation using state-of-the-art neural networks
- How phishing, spam, and malicious emails can be generated using these techniques.
- Detection techniques for neural-network generated malicious emails
Phil Syme
CTO and Co-Founder
Phil Syme has over 22 years of information technology experience. His areas of expertise include system architecture, data processing at scale, and cloud technologies. Phil is the CTO and a cofounder of Area 1 Security, a cloud-based next generation anti-phishing company. Phil was previously a Chief Engineer at Next Century Corporation where he served as a contractor for intelligence agencies. Prior to that he was also co-founder and Principal Engineer at eSymmetrix, and co-authored two introductory programming books. He holds a B.S. in Mathematics and Computer Science from Carnegie Mellon University School of Computer Science.
Detect. Disrupt. Defeat.
No-Phishing Zone
