Sandy Dunn

AI Security & Cyber Risk Quantification

OWASP Top 10 for LLM core team

CISO Advisor  &  Adjunct Prof BSU Cybersecurity

sandy@quarkiq.com

Black Box Dilemma

GenAI Treasure

Sharks

Many Many Many Sharks

OWASP Top 10 for LLM Applications                Plot4AI

Threats

AI Companions

https://beta.character.ai/

Blush & Replika

Use Pricing Calculator

Cost

AI Tools are amazing do jump in!

Be Very Aware & Cautious

Educate your family, friends, business about the GenAI threat from social engineering

Questions ?

Reference

FAQs on Foundation Models and Generative AI Non-Decisional Statement by the National AI Advisory Committee (NAIAC) https://www.ai.gov/wp-content/uploads/2023/09/FAQs-on-Foundation-Models-and-Generative-AI.pdf

andreessen horowitz & ai companions https://a16z.com/how-are-consumers-using-generative-ai/

Cost

https://medium.com/@JT_43697/how-much-do-large-language-models-like-gpt-cost-b3fd252815e5

https://docsbot.ai/tools/gpt-openai-api-pricing-calculator

Research Papers

Universal and Transferable Adversarial Attacks on Aligned Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models https://llm-attacks.org/

Art or Artifice? Large Language Models and the False Promise of Creativity

YouTube Video

AI, Future Tech & Digital Marketing, Matt Wolfe https://www.youtube.com/@mreflow/

Kai Greshake (IN) Security and Misalignment https://www.youtube.com/watch?v=07rnNHnb9rw

MIT Introduction to Deep Learning | 6.S191 https://www.youtube.com/watch?v=QDX-1M5Nj7s&t=36s

MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention https://www.youtube.com/watch?v=ySEx_Bqxvvo&list=WL&index=117&t=1008s

Report Scams

https://www.usa.gov/scams-and-fraud

Risks

Plot4AI https://plot4.ai/

OWASP Top 10 for LLM https://llmtop10.com/

FBI

https://www.ic3.gov/Media/Y2022/PSA220628

Prompt Injection Training & Education

https://github.com/OWASP/www-project-top-10-for-large-language-model-applications/wiki/Vulnerable-LLM-Applications

https://quarkiq.com