{"podcast":{"title":"Software Engineering Institute (SEI) Podcast Series","slug":"software-engineering-institute-sei-podcast-series-389154","podcast_index_feed_id":389154,"rss_url":"https://cmu-sei-podcasts.libsyn.com/rss","website_url":"https://www.sei.cmu.edu/publications/podcasts/index.cfm","image_url":"https://static.libsyn.com/p/assets/4/5/0/6/4506812e834bc5af16c3140a3186d450/5966_Libsyn.png","author":"Carnegie Mellon University Software Engineering Institute","episode_count":435,"summary":"The SEI Podcast Series presents conversations in software engineering, cybersecurity, and future technologies.","last_synced_at":"2026-08-01T02:18:38.616051+00:00","page_url":"https://stenobird.com/podcast/software-engineering-institute-sei-podcast-series-389154"},"episode":{"title":"Protecting AI Systems Against Data Poisoning","slug":"protecting-ai-systems-against-data-poisoning","published_at":"2026-06-04T14:11:00+00:00","page_url":"https://stenobird.com/podcast/software-engineering-institute-sei-podcast-series-389154/protecting-ai-systems-against-data-poisoning","show_page_url":"https://stenobird.com/podcast/software-engineering-institute-sei-podcast-series-389154","url":"https://cmu-sei-podcasts.libsyn.com/protecting-ai-systems-against-data-poisoning","audio_url":"https://traffic.libsyn.com/clean/secure/cmu-sei-podcasts/SEIP_05_05_CUNNINGHAM_2.mp3?dest-id=762491","summary":"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.","meta_description":"Data poisoning—where adversaries tamper with training data to corrupt model behavior—poses significant risks as AI adoption expands across critical sector…","key_points":[],"chapters":[],"topics":[],"duration_seconds":1201,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/software-engineering-institute-sei-podcast-series-389154/episodes/protecting-ai-systems-against-data-poisoning/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/software-engineering-institute-sei-podcast-series-389154/protecting-ai-systems-against-data-poisoning.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}