Protect you Enterprise Cyberworld with ML / Deep learning techniques

With almost all enterprises on the cloud today, enterprise cyber attacks are a reality we cannot ignore. Enterprise security is now more complex than ever before: most enterprise networks comprise hybrid environments with a custom mix of on-premise, data center and SOC installations. Heterogeneity is the key challenge coupled with say, Ransomware attack, financial fraud, theft of sensitive information, service disruption, economic disruption, even state-sponsored espionage. The traditional SIEM solutions based on past history and rules often limit companies to what is known but ever growing and innovative cyber attacks getting evolved are never understood and proactively hunted down. Machine Learning based on deep learning cocktailed with several machine learning techniques opens up an exciting area to effectively detect and prevent such attacks. Due to the vast types and nature of attacks, often one technique is not a solutions. So we as a team of passionate ML enthusiasts were spending enormous amount of time researching, classifying and finding effectively solutions in the exciting world of "Managed Detection and Prevention" based on our cocktail of Deep learning and ML techniques. This session is sharing our experience, learning, mistakes from which we innovated and path that we have taken

1 favorite thumb_down thumb_up 0 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist

Outline/Structure of the Talk

- Cyber security challenges for Enterprises

- Growing threats

- Current solutions and limitations

- Proactive threat hunting with ML techniques

- Key Learning

- Roadmap and opportunities

Learning Outcome

- Deep understanding of cyber security threats

- Limitations of current options

- Opportunity for ML in Cyber security

Target Audience

Enterprise CIOs, ML practitioners

Prerequisites for Attendees

Understanding on cyber world and threats, ML basics, deep learning basics

schedule Submitted 5 days ago

Public Feedback

comment Suggest improvements to the Speaker