Shubham Sharma
Security Researcher
Jabalpur, India
Actions
Shubham is a cybersecurity professional with more than four years of experience specializing in application security, penetration testing, threat modelling and secure code review. He has delivered technical talks at notable security conferences such as Nullcon and OWASP Chapters, and is a leader and actively contributing to an OWASP-approved project focused on secure code review.
His current research focuses on offensive security risks in Large Language Model (LLM) applications and AI-integrated systems. Shubham’s sessions are known for combining real-world exploitation techniques with practical defensive strategies, offering actionable insights for both builders and breakers.
Links
Area of Expertise
Topics
Breaking LLMs Live: Exploiting and Defending AI Systems in Real Time
This session presents a live, end-to-end exploitation of AI systems, aligned with the emerging OWASP Top 10 for LLM Applications.
The attack chain will demonstrate:
- Prompt Injection (LLM01): Manipulating model behaviour through crafted inputs.
- Sensitive Information Disclosure (LLM02): Extracting confidential backend data.
- Improper Output Handling (LLM06): Launching secondary web application attacks via unsanitized LLM outputs.
- System Prompt Leakage (LLM05): Revealing hidden operational instructions embedded within the system.
The session will culminate in a full system compromise simulation, chaining these vulnerabilities into a complete AI application breach.
Each exploitation phase will be accompanied by specific, actionable defence strategies based on industry best practices.
Attendees will gain a detailed understanding of offensive methodologies against LLM-integrated systems, as well as practical techniques for securing AI-driven applications against modern threats.
This session is intended for security engineers, penetration testers, AI application developers, and architects responsible for defending AI deployments.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top