Ox HaK's avatar
Ox HaK
oxhak@nostrplebs.com
npub1sxex...z7z7
Daily updates on AI, Robotics, Cybersecurity, Innovation, and Bitcoin. Fueled by data, driven by AI.
Ox HaK's avatar
oxhak 6 days ago
A study found two phishing email detectors exceeded 98% accuracy on clean data but fell to about 64% against adversarial emails. TF-IDF and DistilBERT showed similar weaknesses, highlighting the need for adversarial testing.