Download to read offline
Uploaded byJuan Carlos Olivares Rojas
Ieee itmsb20
This document discusses the application of artificial intelligence techniques in cybersecurity. It begins by outlining the motivations for applying AI to cybersecurity, such as the growing amounts of data and connections between devices. It then provides an overview of cybersecurity challenges and common AI techniques like machine learning. The document concludes by presenting several examples of how AI is already being used to enhance cybersecurity, such as through anomaly detection, natural language processing for unstructured threat analysis, and AI-powered security analytics tools.
More Related Content
Similar to Ieee itmsb20
![AI_BASED_IDS[1].pptx- artificial intelligence](https://cdn.slidesharecdn.com/ss_thumbnails/aibasedids1-250503172814-a83d1e2b-thumbnail.jpg?width=640&height=640&fit=bounds)
More from Juan Carlos Olivares Rojas
Ieee itmsb20
- 1. Técnicas de InteligenciaArtificial Aplicadas en Ciberseguridad Juan Carlos Olivares Rojas November 2020 SCO
- 2. Introduction CybersecurityAI + =AI Safety & Security
- 3.
- 4. Motivation Everything becomes software-based Everything generates data Everything needs to be secured Everything canbe automated Everything becomes connected Networking Programmability Security Source: Cisco
- 5.
- 6. Motivation Source: Cisco Cybercrime damage estimatedto hit $6 TRILLION BY 2021. 95% of cybersecurity breaches are due to human error. 25 billion connected things will be in use by 2021.
- 7. Motivation Source: Invertia Hackers stolehalf a billion personal records in 2018. 4.07 million cybersecurity jobs are unfilled.
- 8.
- 9.
- 10.
- 11.
- 12.
- 13.
- 14. Threats Initial Code RedWorm Infection Code Red Worm Infection 19 Hours Later
- 15.
- 16.
- 17.
- 18.
- 19.
- 20.
- 21.
- 22.
- 23.
- 24.
- 25.
- 26.
- 27. AI Booming 1. Computingpower What makes AI credible this time around . . . 2. ML, deep learning algorithms 3. Big data 4. Age of the customer/ digital demand 5. Huge investments Source: “Artificial Intelligence Can Finally Unleash Your Business Applications' Creativity” Forrester report
- 28. AI is inCharge Stock Market: 75+% of all trade orders generated by Automated Trading Systems Aviation: Uninterruptible Autopilot System Military: Nuclear Weapons Energy: Nuclear Power Plants Utilities: Water Plants/Electrical Grid Communications: Satellites
- 29. AI Applications Health Personalized medicine,image analytics Manufacturing Predictive and prescriptive maintenance Consumer tech Chatbots Financial services Fraud detection, ID verification Government Cyber-security, smart cities and utilities Energy Seismic and reservoir modeling Service providers Media delivery Retail Video surveillance, shopping patterns
- 30. AI Financial Applications FraudDetection • Real-Time Transactions • Credit Card • Merchant • Collusion • Impersonation • Social Engineering Fraud Risk Modeling & Credit Worthiness Check • Loan Defaults • Delayed Payments • Liquidity • Market & Currencies • Purchases and Payments • Time Series CLV Prediction and Recommendation • Historical Purchase View • Pattern Recognition • Retention Strategy • Upsell • Cross-Sell • Nurturing Customer Segmentation • Behavioral Analysis • Understanding Customer Quadrant • Effective Messaging & Improved Engagement • Targeted Customer Support • Enhanced Retention Other • Image Recognition • NLP • Security • Video Analysis
- 31. AI Development AI More computing power More data New algorithms Whathas changed?A new paradigm
- 32.
- 33.
- 34. AI Ecosystem IT Data Data Platforms DataScience and ML / DL Tools Solutions Genome Research Video SurveillanceCustomer 360 Example Industry Use Cases Fraud Detection HDFS/NFS User Access Security Time to Deploy Multi-Tenant Data DuplicationData Store Cloud Infrastructure
- 35.
- 36.
- 37.
- 38.
- 39.
- 40.
- 41.
- 42.
- 43.
- 44.
- 45. Evolution of securitytechnology - three waves CLOUD, AI and ORCHESTRATION, COLLABORATION INTELLIGENCE and INTEGRATION LAYERED DEFENSES
- 46.
- 47. AI on AttackTools Source: Cisco
- 48. AI and Cybersecurity SecurityAnalytics • Data correlation • Pattern identification • Anomaly detection • Prioritization • Data visualization • Workflow AI: Cognitive Security • Unstructured analysis • Natural language • Question and answer • Machine learning • Bias elimination • Tradeoff analytics Human Expertise • Common sense • Morals • Compassion • Abstraction • Dilemmas • Generalization
- 49.
- 50.
- 51.
- 52. Cisco Security IntelligenceOperations
- 53.
- 54. AI Cybersecurity Solutions WildFire DesktopsLaptopsPhone/TabletServers Cloud Source: WildFire
- 55. Artificial Neural Networks Chen,Y., Abraham, A., & Yang, B. (2007). Hybrid flexible neural-tree-based intrusion detection systems. International Journal of Intelligent Systems, 22, 337–352.
- 56. Stein, G., Chen,B., Wu, A. S., & Hua, K. A. (2005). Decision tree classifier for network intrusion detection with GA-based feature selection. In Paper presented at the proceedings of the 43rd annual Southeast regional conference. Kennesaw, Georgia. Randomly Generated Population Feature Selection Decision Tree Constructor Decision Tree Evaluator Fitness Computation Final Decision Tree Classifier Training Data Validation Data Testing Data Generate Next Generation GA/Decision Tree Hybrid Genetic Algorithms
- 57. Teache r Correct (No Training) Winner (Decision) w1 w2w3 wn Φ1 Φ2 Φ3 Φn Y(1) Y(2) Y(3) Y(n) X(1) X(2) X(3) X(4) Incorrect (Training Needed) Chavan, Sampada, et al. "Adaptive neuro-fuzzy intrusion detection systems. "Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004. International Conference on. Vol. 1. IEEE, 2004. Neuro-fuzzing
- 58. Support Vector Machine Decision Trees Intrusion Detection Data HybridDecision Tree SVM Approach Peddabachigari, Sandhya, et al. "Modeling intrusion detection system using hybrid intelligent systems." Journal of network and computer applications 30.1 (2007): 114-132. Hybrid
- 59. Shon, T., &Moon, J. (2007). A hybrid machine learning approach to network anomaly detection. Information Sciences, 177, 3799–3821. Hybrid ML NAD
- 60. Multiple Classifier Systemfor Intrusion Detection Intrusion Detection as a Pattern Recognition Problem Giacinto, Giorgio, Fabio Roli, and Luca Didaci. "Fusion of multiple classifiers for intrusion detection in computer networks." Pattern recognition letters 24.12 (2003): 1795-1803. Pattern Recognition
- 61. Neural Networks (Backpropagation) Neural Networks(Scale Conjugate Gradient) Neural Network (One Step Secant) Support Vector Machine Multivariate Regression Splines Ensemble Data preprocessor Mukkamala, Srinivas, Andrew H. Sung, and Ajith Abraham. "Intrusion detection using an ensemble of intelligent paradigms." Journal of network and computer applications 28.2 (2005): 167-182. Ensemble
- 62.
- 63. Questions? Thanks you somuch! juan.or@morelia.tecnm.mx, jcolivares@computer.org, jcolivares@ieee.org