Forensicability of Deep Neural Network Inference Pipelines
We propose methods to infer properties of the execution environment of machine learning pipelines by tracing characteristic numerical deviations in observable outputs. Results from a series of proof-of-concept experiments obtained on local and cloud-hosted machines give rise to possible forensic applications, such as the identification of the hardware platform used to produce deep neural network predictions. Finally, we introduce boundary samples that amplify the numerical deviations in order to distinguish machines by their predicted label only.
Code (1)
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Forensicability Assessment of Questioned Images in Recapturing Detection
Recapture detection of face and document images is an important forensic task. With deep learning, the performances of face anti-spoofing (FAS) and recaptured document detection have been improved significantly. However,…
Face Anti-SpoofingImage Quality AssessmentStatistical Testing Framework for Clustering Pipelines by Selective Inference
A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating multiple analysis algorithms. In many practical applications, analytical findings are obtained o…
Outlier DetectionStrategies for Optimizing End-to-End Artificial Intelligence Pipelines on Intel Xeon Processors
End-to-end (E2E) artificial intelligence (AI) pipelines are composed of several stages including data preprocessing, data ingestion, defining and training the model, hyperparameter optimization, deployment, inference, po…
Hyperparameter OptimizationRecommendation SystemsAutomated Heterogeneous Low-Bit Quantization of Multi-Model Deep Learning Inference Pipeline
Multiple Deep Neural Networks (DNNs) integrated into single Deep Learning (DL) inference pipelines e.g. Multi-Task Learning (MTL) or Ensemble Learning (EL), etc., albeit very accurate, pose challenges for edge deployment…
Ensemble LearningMulti-Task LearningQuantizationIPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency
Efficiently optimizing multi-model inference pipelines for fast, accurate, and cost-effective inference is a crucial challenge in machine learning production systems, given their tight end-to-end latency requirements. To…
Deep Learning