Protecting AI Systems Against Data Poisoning

Protecting AI Systems Against Data Poisoning

From Software Engineering Institute (SEI) Podcast Series by Members of Technical Staff at the Software Engineering Institute

June 4, 2026 · 20 min

About this episode

This episode discusses the risks of data poisoning in AI systems and explores mitigation strategies.

Data poisoning—where adversaries tamper with training data to corrupt model behavior—poses significant risks as AI adoption expands across critical sectors. Organizations without mechanisms in place to detect or prevent data poisoning are open to an avenue of attack that, once exploited, is difficult to remedi ate . Machine unlearning and model retraining are not always viable or effective solutions . In today's operational climate , where threat actors look to influence models and degrade the trust of users through incorrect behaviors, preventing data poisoning is more important than ever. In this episode of the SEI Podcast Series, Julie Lawler and James Cunningham—AI security researchers at Carnegie Mellon University's Software Engineering Institute—discuss the growing threat of data poisoning in AI systems and highlight emerging mitigation strategies , including chain-of-custody controls.

People in this episode

Guests: Julie Lawler, James Cunningham

Topics covered

  • AI security
  • data poisoning
  • mitigation strategies
  • machine learning
  • model behavior

Keywords

  • data poisoning
  • AI systems
  • model retraining
  • machine unlearning
  • security threats

Mentioned in this episode

Organizations: Carnegie Mellon University, Software Engineering Institute

More episodes of Software Engineering Institute (SEI) Podcast Series

Explore listener stats, chart rankings, contacts and more on the Software Engineering Institute (SEI) Podcast Series podcast page.