Con-Detect: Detecting Adversarially Perturbed Natural Language Inputs to Deep Classifiers Through Holistic Analysis حسب Hassan Ali (3348749)

"…Even in the worst case, we note a 100% increase in the required number of queries and a 50% increase in the number of words perturbed, suggesting that Con-Detect is hard to evade. …"

Con-Detect: Detecting adversarially perturbed natural language inputs to deep classifiers through holistic analysis حسب Hassan, Ali

"…Even in the worst case, we note a 100% increase in the required number of queries and a 50% increase in the number of words perturbed, suggesting that Con-Detect is hard to evade.…"
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل