ML-On-Rails: Safeguarding Machine Learning Models in Software Systems A Case Study

• URL: http://arxiv.org/abs/2401.06513v1
• Date: Fri, 12 Jan 2024 11:27:15 GMT
• Title: ML-On-Rails: Safeguarding Machine Learning Models in Software Systems A Case Study
• Authors: Hala Abdelkader, Mohamed Abdelrazek, Scott Barnett, Jean-Guy Schneider, Priya Rani, Rajesh Vasa
• Abstract summary: We introduce ML-On-Rails, a protocol designed to safeguard machine learning models. ML-On-Rails establishes a well-defined endpoint interface for different ML tasks, and clear communication between ML providers and ML consumers. We evaluate the protocol through a real-world case study of the MoveReminder application.
• Score: 4.087995998278127
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning (ML), especially with the emergence of large language models (LLMs), has significantly transformed various industries. However, the transition from ML model prototyping to production use within software systems presents several challenges. These challenges primarily revolve around ensuring safety, security, and transparency, subsequently influencing the overall robustness and trustworthiness of ML models. In this paper, we introduce ML-On-Rails, a protocol designed to safeguard ML models, establish a well-defined endpoint interface for different ML tasks, and clear communication between ML providers and ML consumers (software engineers). ML-On-Rails enhances the robustness of ML models via incorporating detection capabilities to identify unique challenges specific to production ML. We evaluated the ML-On-Rails protocol through a real-world case study of the MoveReminder application. Through this evaluation, we emphasize the importance of safeguarding ML models in production.

Related papers

• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [70.19607283302712]
  We propose a novel framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM. We also propose a three-stage training scheme to fully exploit the potential of s-MLLM.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration [90.36429361299807]
  multimodal large language models (MLLMs) have demonstrated remarkable success in engaging in conversations involving visual inputs. The integration of visual modality has introduced a unique vulnerability: the MLLM becomes susceptible to malicious visual inputs. We introduce a technique termed CoCA, which amplifies the safety-awareness of the MLLM by calibrating its output distribution.
  arXiv  Detail & Related papers  (2024-09-17T17:14:41Z)
• A Large-Scale Study of Model Integration in ML-Enabled Software Systems [4.776073133338119]
  Machine learning (ML) and its embedding in systems has drastically changed the engineering of software-intensive systems. Traditionally, software engineering focuses on manually created artifacts such as source code and the process of creating them. We present the first large-scale study of real ML-enabled software systems, covering over 2,928 open source systems on GitHub.
  arXiv  Detail & Related papers  (2024-08-12T15:28:40Z)
• Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
  We introduce the framework of verbalized machine learning (VML) VML constrains the parameter space to be human-interpretable natural language. We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
  arXiv  Detail & Related papers  (2024-06-06T17:59:56Z)
• When Code Smells Meet ML: On the Lifecycle of ML-specific Code Smells in ML-enabled Systems [13.718420553401662]
  We aim to investigate the emergence and evolution of specific types of quality-related concerns known as ML-specific code smells. More specifically, we present a plan to study ML-specific code smells by empirically analyzing their prevalence in real ML-enabled systems. We will conduct an exploratory study, mining a large dataset of ML-enabled systems and analyzing over 400k commits about 337 projects.
  arXiv  Detail & Related papers  (2024-03-13T07:43:45Z)
• MLGuard: Defend Your Machine Learning Model! [3.4069804433026314]
  We propose MLGuard, a new approach to specify contracts for Machine Learning applications. Our work is intended to provide the overarching framework required for building ML applications and monitoring their safety.
  arXiv  Detail & Related papers  (2023-09-04T06:08:11Z)
• Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review [51.31851488650698]
  Machine learning (ML) sees an increasing prevalence of being used in the internet-of-things (IoT)-based smart grid. adversarial distortion injected into the power signal will greatly affect the system's normal control and operation. It is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems.
  arXiv  Detail & Related papers  (2023-08-30T03:29:26Z)
• Scaling up Trustless DNN Inference with Zero-Knowledge Proofs [47.42532753464726]
  We present the first practical ImageNet-scale method to verify ML model inference non-interactively, i.e., after the inference has been done. We provide the first ZKSNARK proof of valid inference for a full resolution ImageNet model, achieving 79% top-5 accuracy.
  arXiv  Detail & Related papers  (2022-10-17T00:35:38Z)
• Practical Machine Learning Safety: A Survey and Primer [81.73857913779534]
  Open-world deployment of Machine Learning algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities. New models and training techniques to reduce generalization error, achieve domain adaptation, and detect outlier examples and adversarial attacks. Our organization maps state-of-the-art ML techniques to safety strategies in order to enhance the dependability of the ML algorithm from different aspects.
  arXiv  Detail & Related papers  (2021-06-09T05:56:42Z)
• Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development [6.903929927172917]
  We present a method consisting of eight design questions that outline the deliberation and normative choices going into creating a machine learning model. Our method affords several benefits, such as supporting critical assessment through methodological transparency. We believe that our method can help ML practitioners structure and justify their choices and assumptions when developing ML models.
  arXiv  Detail & Related papers  (2021-05-03T08:47:45Z)
• MLDemon: Deployment Monitoring for Machine Learning Systems [10.074466859579571]
  We propose a novel approach, MLDemon, for ML DEployment MONitoring. MLDemon integrates both unlabeled features and a small amount of on-demand labeled examples over time to produce a real-time estimate. On temporal datasets with diverse distribution drifts and models, MLDemon substantially outperforms existing monitoring approaches.
  arXiv  Detail & Related papers  (2021-04-28T07:59:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.