Securing AI Agents: Exploring Critical Threats and Exploitation Techniques

No ratings

Presented at BSides SF 2025 by

Naveen Mahavishnu

Mohankumar Vengatachalam

Our talk will focus on securing autonomous AI agents by addressing their unique threats. We will dive into threat modeling of real-world autonomous AI systems, model poisoning attacks with hacking demos, and then explore advanced prompt injection techniques and mitigation strategies.