07What are data poisoning and ML supply-chain attacks, and how do you defend against them?▼hard★ EssentialGoogleMicrosoftAnthropic1 repliesunlockedMost ML security centers on inference-time attacks; this one targets the training pipeline, where a poisoned dataset or a tampered dependency can hide a backdoor that clean-data evaluation never catches. What lands is naming the attack classes and recognizing that defense means provenance, not a single model fix.Open full answer →
45What are backdoor (trojan) attacks on ML models, and how do you detect a poisoned model?▼hardGoogleMicrosoftAnthropic1 replies◆ premiumA backdoored model acts perfectly until it meets a secret trigger, then flips. The signal is explaining why clean test accuracy never exposes it, and what detection actually buys you when the trigger is unknown.Open full answer →
