False positive sensitive training of neural networks for malicious prompt classification
AssigneePalo Alto Networks, Inc.
InventorsBrody James Kutt, Samarth Keshari, Yazdan Jamshidikhezeli, Sergey Sviridov
Life of this patent
Estimating the term…
Loading patent…
AssigneePalo Alto Networks, Inc.
InventorsBrody James Kutt, Samarth Keshari, Yazdan Jamshidikhezeli, Sergey Sviridov
Estimating the term…
A double cross-entropy loss function is a modification of the standard cross-entropy loss function that is tunable to penalize specific error types, i.e., false positives and false positives for binary classification. A prompt classifier is trained using the double cross-entropy loss function to classify prompts as malicious or benign. The double cross-entropy loss function for the prompt classifier is tuned so that false positive classifications are heavily penalized. The resulting trained prompt classifier maintains a high true positive rate while having a classification threshold that keeps the false positive rate very small. The trained prompt classifier is deployed in a high-load environment for prompt classification.
A method comprising:
A non-transitory, machine-readable medium having program code stored thereon, the program code comprising instructions to:
An apparatus comprising:
Dependencies are inferred from the claim text.