AI Data Attacks: Poison the Data, or Just Swap the Model File
AI data attacks explained: how poisoning hits each stage of an ML pipeline, plus a hands-on lab where a malicious pickle model file runs code the moment you load it.
5 write-ups tagged Machine Learning Security. Browse all tags or the full blog.
AI data attacks explained: how poisoning hits each stage of an ML pipeline, plus a hands-on lab where a malicious pickle model file runs code the moment you load it.
Topic 6 of my AI track: cleaning messy network logs with pandas, encoding and splitting them, training a threat classifier, and why accuracy lies in security.
Clean label attacks poison the features and keep the labels plausible, so one chosen input flips while accuracy barely moves. Build one and learn to defend it.
Label flipping poisons a model's labels, not its features. Flip 40% of one class in a lab, watch a 99% model drop to 81%, and learn to detect and defend it.
I poisoned 3.29% of a spam filter's training data and planted a working backdoor. Accuracy stayed at 94.12%, and my canary tests all passed.