Open Source in Finance Forum London 2024

In the rapidly evolving AI field, Large Language Models (LLMs) like GPT and BERT drive applications from natural language processing to generative content, presenting unique security challenges highlighted by the OWASP Top 10 for LLM Applications. This talk will dissect critical security vulnerabilities specific to LLMs, using real-world scenarios to demonstrate how these can be exploited, including adversarial attacks and privacy breaches. Attendees will gain a comprehensive understanding of LLM security terrain, enhanced by live hacking demonstrations, showing the practical implications of theoretical vulnerabilities. Key Takeaways: - Deep insights into OWASP's top security vulnerabilities for LLMs. - The impact of these vulnerabilities on businesses and users, underlining the need for strong security measures. - Hands-on knowledge to defend against LLM-specific attacks, featuring live demo hacking techniques and their countermeasures.