IP Library Granted Patent US 12,626,095
Granted Patent B2
US 12,626,095 · App. 17/492,294 · Granted May 12, 2026

Machine learning outputs with high confidence explanations

Inventor: Tomas Pevny (Prague, CZ)
Assignee: Gen Digital Inc.
G06N3/045
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,626,095
App. No.
17/492,294
Granted
May 12, 2026
Kind
B2
Abstract

A malware classification system provides improved confidence in explanations of neural network classification outputs using methods such as weighting or masking when training the neural network to train the network on a sample resembling or including the explanation. The explanation in some examples comprises a subset of a hierarchical input vector that is responsible for the neural network's classification output. In another example the neural network has an inner portion configured to reduce the weight of elements of the output not significantly contributing to the explanation of the output, such as by reducing the weight of as many such outputs to zero as is practical in generating the desired output.

Claims (34)

1 . A method of generating an explanation of output from a machine-learning system, comprising:

receiving an input data string having a hierarchical structure;

analyzing the input data string using a machine learning module to automatically generate an output corresponding to the received input data string;

generating an explanation of the output comprising a subset of the input data string that is responsible for the output; and

training the machine learning module using a loss function optimized with an inner optimization that generates a sparse output corresponding to the explanation of the output, wherein the explanation comprises a subset of the input data string selected according to hierarchical groupings within the input data string, and wherein the training uses the explanation as a training input to update the machine learning module based on the hierarchical structure.

2 . The method of generating an explanation of output from a machine-learning system of claim 1 , further comprising applying a weighting or masking function when training the machine learning module using the generated explanation of the output and the output, configured to improve the output generated when the generated explanation of output is provided as input.

3 . The method of generating an explanation of output from a machine-learning system of claim 2 , wherein the loss function used to train the machine learning module is optimized using an inner optimization for an estimated output and the weighting or masking function.

4 . The method of generating an explanation of output from a machine-learning system of claim 3 , wherein the loss function optimization is trained using second-order stochastic gradient descent.

5 . The method of generating an explanation of output from a machine-learning system of claim 1 , further comprising constructing the machine learning module using a hierarchy of the input data string.

6 . The method of generating an explanation of output from a machine-learning system of claim 1 , wherein the machine learning module is a neural network.

7 . The method of generating an explanation of output from a machine-learning system of claim 6 , wherein the neural network comprises a hierarchical multiple-instance-learning neural network.

8 . The method of generating an explanation of output from a machine-learning system of claim 7 , wherein the neural network comprises an outer optimization of a loss function, and an inner optimization for one or more parameters of the loss function.

9 . The method of generating an explanation of output from a machine-learning system of claim 6 , wherein generating an explanation of the output is performed using logic other than the neural network.

10 . A method of generating an explanation of output from a machine-learning system, comprising:

receiving an input data string having a hierarchical structure;

analyzing the input data string using a machine learning module to automatically generate an output corresponding to the received input data string; and

generating an explanation of the output comprising a subset of the input data string that is responsible for the output;

the machine learning module comprising a neural network having an inner portion and an outer portion, wherein the inner portion is configured to reduce or zero the weight of elements of the output while still producing a desired output and wherein the outer portion aggregates a sparse output vector to produce a classification output, wherein the inner portion generates instance-level outputs that correspond to hierarchical segments of the input data string and are reduced or zeroed based on the hierarchical groupings, and wherein the outer portion aggregates the instance-level outputs according to the hierarchical structure.

11 . The method of generating an explanation of output from a machine-learning system, of claim 10 , wherein reducing or zeroing the weight of elements of the output while still producing a desired output comprises reducing the weight to zero.

12 . The method of generating an explanation of output from a machine-learning system, of claim 11 , wherein reducing or zeroing the weight of elements of the output while still producing a desired output to zero comprises reducing the weights of as many elements of the output to zero as can be achieved while still generating the desired output.

13 . The method of generating an explanation of output from a machine-learning system, of claim 10 , further comprising regularizing one or more outputs of the inner layer to be either zero or the largest observed value in an inner layer output vector comprising the one or more outputs of the inner layer.

14 . The method of generating an explanation of output from a machine-learning system of claim 10 , further comprising constructing the machine learning module using a hierarchy of the input data string.

15 . The method of generating an explanation of output from a machine-learning system of claim 10 , wherein the machine learning module is a neural network.

16 . The method of generating an explanation of output from a machine-learning system of claim 15 , wherein the neural network comprises a hierarchical multiple-instance-learning neural network.

17 . The method of generating an explanation of output from a machine-learning system of claim 15 , wherein the inner portion outputs instances of the input and the outer portion outputs aggregated output of the inner portion.

18 . The method of generating an explanation of output from a machine-learning system of claim 10 , wherein the inner portion and the outer portion of the machine learning module are configured to improve the confidence of the machine learning module in the explanation.

19 . The method of generating an explanation of output from a machine-learning system of claim 10 , wherein the inner portion and outer portion of the machine learning module are configured to reduce the size of explanation of output.

20 . A machine learning system, comprising:

a processor and a memory; and

a machine-readable medium with instructions stored thereon, the instructions when executed on the processor operable to cause the processor to:

receive an input data string having a hierarchical structure;

analyze the input data string using a machine learning module to automatically generate an output corresponding to the received input data string;

generate an explanation of the output comprising a subset of the input data string that is responsible for the output; and

train the machine learning module using the generated explanation of the output and the output, wherein the explanation is used as a training input and wherein the machine learning module comprises a neural network with an inner portion producing a sparse output corresponding to an explanation of the output and an outer portion aggregating the sparse output to produce the classification, wherein the inner portion produces a sparse output corresponding to an explanation that comprises a subset of the input data string selected according to hierarchical groupings within the input data string, and wherein the explanation is provided as a training input to update the neural network using the hierarchical structure of the input data string.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 30, 2025
From: GEN DIGITAL AMERICAS S.R.O.
To: GEN DIGITAL INC.
Reel/Frame 071771/0767 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 30, 2025
From: AVAST SOFTWARE S.R.O.
To: GEN DIGITAL AMERICAS S.R.O.
Reel/Frame 071777/0341 →
Continuity (1)
Related Publication 20230104673A1 · Apr 6, 2023
References Cited (25)
US 20180365560A1 · Qiao · 2018 [cited by examiner]
US 20190354805A1 · Hind · 2019 [cited by examiner]
US 20200364616A1 · Wong · 2020 [cited by examiner]
US 20220114595A1 · Balayan · 2022 [cited by examiner]
US 20230056772A1 · Zhu · 2023 [cited by examiner]
WO WO2023277905A1 · 2023 [cited by examiner]
Jaromir Janisch, Tomas Pevny and Viliam Lisy, “Cost-Efficient Hierarchical Knowledge Extraction with Deep Reinforcement Learning”, Artificial Intelligence Center, Department of Computer Science, pp. 2-3 (Year: 2020). [cited by examiner]
Leon Bottou, “Large-Scale Machine Learning with Stochastic Gradient Descent”, 2010, NEC Labs America, pp. 1 & 7 (Year: 2010). [cited by examiner]
Xu, D., Shi, Y., Tsang, I. W., Ong, Y. S., Gong, C., & Shen, X. (2019). Survey on multi-output learning. IEEE transactions on neural networks and learning systems, 31(7), 2409-2429. (Year: 2019). [cited by examiner]
Sun, Jiamei, et al. “Explanation-guided training for cross-domain few-shot classification.” 2020 25th international conference on pattern recognition (ICPR). IEEE, 2021 (Year: 2021). [cited by examiner]
Meister, Clara, et al. “Is sparse attention more interpretable?.” arXiv preprint arXiv:2106.01087 (Year: 2021). [cited by examiner]
Kohlbrenner, Maximilian, et al. “Towards best practice in explaining neural network decisions with LRP.” 2020 international joint conference on neural networks (IJCNN). IEEE (Year: 2020). [cited by examiner]
Ketepalli, Gayatri, and Premamayudu Bulla. “Review on Generative Deep Learning Models and Datasets for Intrusion Detection Systems.” Revue d'Intelligence Artificielle 34.2 (Year: 2020). [cited by examiner]
Kuppa, Aditya, and Nhien-An Le-Khac. “Adversarial XAI methods in cybersecurity.” IEEE transactions on information forensics and security 16 (2021): 4924-4938 (Year: 2021). [cited by examiner]
Warnecke, Alexander, et al. “Evaluating explanation methods for deep learning in security.” 2020 IEEE european symposium on security and privacy (EuroS&P). IEEE (Year: 2020). [cited by examiner]
Amich, Abderrahmen, and Birhanu Eshete. “Explanation-guided diagnosis of machine learning evasion attacks.” International Conference on Security and Privacy in Communication Systems. Cham: Springer International Publish… [cited by examiner]
Ijaz, Muhammad, Muhammad Hanif Durad, and Maliha Ismail. “Static and dynamic malware analysis using machine learning.” 2019 16th International bhurban conference on applied sciences and technology (IBCAST). IEEE (Year: … [cited by examiner]
Li, Dongfang, et al. “Towards faithful explanations for text classification with robustness improvement and explanation guided training.” arXiv preprint arXiv:2312.17591 (Year: 2023). [cited by examiner]
Binder, Alexander, et al. “Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers.” International Conference on Artificial Neural Networks. Springer, Cham, 2016. [cited by applicant]
Riberio, Marco Tulio, et al. “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. Knowledge Discovery and Data Mining. KDD 2016 San Francisco, CA. [cited by applicant]
Belanger, et al. “End-to-End Learning for Structured Prediction Energy Networks” Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia, PMLR 70, 2017. [cited by applicant]
Kawaguchi, et al. “Generalization in Deep Learning” arXiv preprint arXiv:170.05468, 2017. [cited by applicant]
Lundberg, Scott M and Su-In Lee. A Unified Approach to Interpreting Model Predictions. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA. [cited by applicant]
Chang, et al. “A Game Theoretic Approach to Class-wise Selective Rationalization” 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada. [cited by applicant]
Ying, Rex, et al. “Gnn Explainer: A tool for post-hoc explanation of graph neural networks.” arXiv preprint arXiv:1903.03894, 2019. [cited by applicant]