מה צריך לדעת לפני
שתתחיל

מתחיל 4 June 2026 09:01

נגמר 4 June 2026

00 ימים
00 שעות
00 דקות
00 שניות
course image

Safety of GenAI Through the Lens of Security and Cryptography

Immerse yourself in an enlightening session with Somesh Jha from the University of Wisconsin-Madison, focusing on the safety challenges faced by Generative AI. This course examines how security and cryptography frameworks can address safety concerns in AI development. Available exclusively on YouTube, it is a must-watch for enthusiasts of Arti.
Simons Institute via YouTube

Simons Institute

6076 קורסים


1 hour 6 minutes

שדרוג אופציונלי זמין

Not Specified

התקדמות בקצב שלך

Free Video

שדרוג אופציונלי זמין

סקירה כללית

Immerse yourself in an enlightening session with Somesh Jha from the University of Wisconsin-Madison, focusing on the safety challenges faced by Generative AI. This course examines how security and cryptography frameworks can address safety concerns in AI development.

Available exclusively on YouTube, it is a must-watch for enthusiasts of Artificial Intelligence and Computer Science.

סילבוס

  • Introduction to Generative AI
  • Fundamental concepts of Generative AI
    Overview of current applications and challenges
  • Key Concepts in Security and Cryptography
  • Basic principles of computer security
    Cryptographic techniques and protocols
  • Security Risks in Generative AI
  • Attack vectors specific to GenAI
    Case studies of security breaches in AI systems
  • Cryptographic Methods for Securing GenAI
  • Encryption techniques for protecting AI models and data
    Digital signatures and authentication for AI systems
  • Data Privacy and GenAI
  • Differential privacy in AI applications
    Privacy-preserving machine learning techniques
  • Risk Assessment in GenAI Systems
  • Identifying and evaluating potential security risks
    Developing risk mitigation strategies
  • Adversarial Attacks and Defenses in GenAI
  • Types of adversarial attacks on AI models
    Defense mechanisms and robust model design
  • Secure Design of GenAI Models
  • Principles of secure software development for AI
    Best practices for securing AI model lifecycle
  • Regulatory and Ethical Considerations
  • Compliance with data protection laws
    Ethical implications of GenAI deployment
  • Emerging Trends in AI Safety and Security
  • Advances in cryptography related to AI
    Future directions for GenAI safety research
  • Case Studies and Applications
  • Real-world applications and implications of secured GenAI systems
    Lessons learned from past incidents
  • Conclusion and Future Directions
  • Summary of key learnings
    Potential future developments in GenAI security
  • Final Project/Assessment
  • Practical exercise or project to apply course concepts
    Evaluation criteria and project presentation guidelines

נושאים

Computer Science