<p>Modern AI systems don’t just rely on static datasets - they depend on continuous streams of real-time data to train and update models and make decisions. But what happens when that data can’t be trusted?</p> <p>In this talk, Olena Kutsenko explores how streaming data pipelines - often built on systems like Apache Kafka - are becoming a critical yet insufficiently secured attack vector for AI-driven applications.</p> <p>Rather than targeting models directly, attackers can manipulate the data flowing into them. By injecting, modifying, or replaying events in real-time streams, adversaries can:</p> <ul> <li>Poison training data and degrade model accuracy over time</li> <li>Manipulate real-time features used in fraud detection or recommendation systems</li> <li>Trigger unintended behaviors in downstream AI systems</li> <li>Quietly influence decisions without ever touching the model itself</li> </ul> <p>Olena will examine how these attacks work in practice, from subtle data drift manipulation to targeted event injection, and why they are difficult to detect using traditional security tools.</p> <p>The talk will break down the weak points in modern data pipelines:</p> <ul> <li>Lack of validation and trust boundaries in event streams</li> <li>Over-reliance on infrastructure-level security, such as encryption and access control lists (ACLs)</li> <li>Blind spots in monitoring data integrity and semantic correctness</li> </ul> <p>She will also explore how these risks evolve in systems that continuously retrain or adapt, where corrupted data doesn’t just affect a single decision but becomes embedded in the model itself.</p> <p>Finally, Olena will discuss defensive strategies that go beyond securing infrastructure: treating data as an attack surface, implementing validation and anomaly detection at the data level, and designing pipelines that can detect and recover from adversarial inputs.</p> <p>This talk offers a new perspective on AI security - not by focusing on models, but on the data pipelines that feed them, where some of the most impactful and least visible attacks can occur.</p>