Page 10 of 13
Adversarial ML
Evasion, data poisoning, backdoors and model extraction, with a lab that backdoors a classifier using 1% poisoned data, detects it three ways and repairs it.
43 min read · October 17, 2026
Page 10 of 13
Evasion, data poisoning, backdoors and model extraction, with a lab that backdoors a classifier using 1% poisoned data, detects it three ways and repairs it.
43 min read · October 17, 2026