Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges

• URL: http://arxiv.org/abs/2506.02032v1
• Date: Fri, 30 May 2025 17:45:31 GMT
• Title: Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges
• Authors: Raj Patel, Himanshu Tripathi, Jasper Stone, Noorbakhsh Amiri Golilarz, Sudip Mittal, Shahram Rahimi, Vini Chaudhary,
• Abstract summary: We present a systematic application of the MITRE ATLAS (Adrial Threat Landscape for Artificial-Intelligence Systems) framework to assess attacks across different phases of the MLOps ecosystem.<n>We then present a structured taxonomy of attack techniques explicitly mapped to corresponding phases of the MLOps ecosystem.<n>This is followed by a taxonomy of mitigation strategies aligned with these attack categories, offering actionable early-stage defenses to strengthen the security of MLOps ecosystem.
• Score: 4.6592774515395465
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid adoption of machine learning (ML) technologies has driven organizations across diverse sectors to seek efficient and reliable methods to accelerate model development-to-deployment. Machine Learning Operations (MLOps) has emerged as an integrative approach addressing these requirements by unifying relevant roles and streamlining ML workflows. As the MLOps market continues to grow, securing these pipelines has become increasingly critical. However, the unified nature of MLOps ecosystem introduces vulnerabilities, making them susceptible to adversarial attacks where a single misconfiguration can lead to compromised credentials, severe financial losses, damaged public trust, and the poisoning of training data. Our paper presents a systematic application of the MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) framework, a comprehensive and continuously updated catalog of AI-focused attacks, to systematically assess attacks across different phases of the MLOps ecosystem. We begin by examining the preparatory phases during which adversaries acquire the essential intelligence required to initiate their attacks. We then present a structured taxonomy of attack techniques explicitly mapped to corresponding phases of the MLOps ecosystem, supported by examples drawn from red-teaming exercises and real-world incidents. This is followed by a taxonomy of mitigation strategies aligned with these attack categories, offering actionable early-stage defenses to strengthen the security of MLOps ecosystem. Given the rapid evolution and adoption of MLOps, we further highlight key research gaps that require immediate attention. Our work emphasizes the importance of implementing robust security protocols from the outset, empowering practitioners to safeguard MLOps ecosystem against evolving cyber attacks.

Related papers

• Preliminary Investigation into Uncertainty-Aware Attack Stage Classification [81.28215542218724]
  This work addresses the problem of attack stage inference under uncertainty.<n>We propose a classification approach based on Evidential Deep Learning (EDL), which models predictive uncertainty by outputting parameters of a Dirichlet distribution over possible stages.<n>Preliminary experiments in a simulated environment demonstrate that the proposed model can accurately infer the stage of an attack with confidence.
  arXiv  Detail & Related papers  (2025-08-01T06:58:00Z)
• A Survey on Model Extraction Attacks and Defenses for Large Language Models [55.60375624503877]
  Model extraction attacks pose significant security threats to deployed language models.<n>This survey provides a comprehensive taxonomy of extraction attacks and defenses, categorizing attacks into functionality extraction, training data extraction, and prompt-targeted attacks.<n>We examine defense mechanisms organized into model protection, data privacy protection, and prompt-targeted strategies, evaluating their effectiveness across different deployment scenarios.
  arXiv  Detail & Related papers  (2025-06-26T22:02:01Z)
• From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem [3.3821226324715403]
  Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents.<n>This paper presents a systematic survey of the growing complexity of jailbreak attacks and corresponding defense mechanisms within the expanding LLM ecosystem.
  arXiv  Detail & Related papers  (2025-06-18T06:33:19Z)
• A Large Language Model-Supported Threat Modeling Framework for Transportation Cyber-Physical Systems [11.872361272221244]
  TraCR-TMF (Transportation Cybersecurity and Resiliency Threat Modeling Framework) is a large language model (LLM)-based framework that minimizes expert intervention.<n>It identifies threats, potential attack techniques, and corresponding countermeasures by leveraging the MITRE ATT&CK matrix.<n>TraCR-TMF also maps attack paths to critical assets by analyzing vulnerabilities using a customized LLM.
  arXiv  Detail & Related papers  (2025-06-01T04:33:34Z)
• Attack and defense techniques in large language models: A survey and new perspectives [5.600972861188751]
  Large Language Models (LLMs) have become central to numerous natural language processing tasks, but their vulnerabilities present security and ethical challenges.<n>This systematic survey explores the evolving landscape of attack and defense techniques in LLMs.
  arXiv  Detail & Related papers  (2025-05-02T03:37:52Z)
• Robust Intrusion Detection System with Explainable Artificial Intelligence [0.0]
  Adversarial input can exploit machine learning (ML) models through standard interfaces.<n> Conventional defenses such as adversarial training are costly in computational terms and often fail to provide real-time detection.<n>We suggest a novel strategy for detecting and mitigating adversarial attacks using eXplainable Artificial Intelligence (XAI)
  arXiv  Detail & Related papers  (2025-03-07T10:31:59Z)
• A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments [55.60375624503877]
  Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data.<n>This survey is motivated by the urgent need to understand how the unique characteristics of cloud, edge, and federated deployments shape attack vectors and defense requirements.<n>We systematically examine the evolution of attack methodologies and defense mechanisms across these environments, demonstrating how environmental factors influence security strategies in critical sectors such as autonomous vehicles, healthcare, and financial services.
  arXiv  Detail & Related papers  (2025-02-22T03:46:50Z)
• Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics [68.36528819227641]
  This paper systematically quantifies the robustness of VLA-based robotic systems.<n>We introduce two untargeted attack objectives that leverage spatial foundations to destabilize robotic actions, and a targeted attack objective that manipulates the robotic trajectory.<n>We design an adversarial patch generation approach that places a small, colorful patch within the camera's view, effectively executing the attack in both digital and physical environments.
  arXiv  Detail & Related papers  (2024-11-18T01:52:20Z)
• A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends [78.3201480023907]
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. The vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of the various forms of existing LVLM attacks.
  arXiv  Detail & Related papers  (2024-07-10T06:57:58Z)
• The Malware as a Service ecosystem [5.973995274784383]
  The study emphasises the profound challenges MaaS poses to traditional cybersecurity defences. There is a call for a paradigm shift in defensive strategies, advocating for dynamic analysis, behavioural detection, and the integration of AI and machine learning techniques. The ultimate goal is to aid in developing more effective strategies for combating the spread of commoditised malware threats.
  arXiv  Detail & Related papers  (2024-05-07T08:25:12Z)
• Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems [8.584570228761503]
  transferable attacks pose severe risks to security, privacy, and system integrity.<n>This survey delivers the first comprehensive review of transferable attacks across seven major categories.<n>We examine both the underlying mechanics and practical implications of transferable attacks on AI systems.
  arXiv  Detail & Related papers  (2023-11-20T14:29:45Z)
• Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective [69.25513235556635]
  Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans. Some paradigms have been recently developed to explore this adversarial phenomenon occurring at different stages of a machine learning system. We propose a unified mathematical framework to covering existing attack paradigms.
  arXiv  Detail & Related papers  (2023-02-19T02:12:21Z)
• Towards Automated Classification of Attackers' TTPs by combining NLP with ML Techniques [77.34726150561087]
  We evaluate and compare different Natural Language Processing (NLP) and machine learning techniques used for security information extraction in research. Based on our investigations we propose a data processing pipeline that automatically classifies unstructured text according to attackers' tactics and techniques.
  arXiv  Detail & Related papers  (2022-07-18T09:59:21Z)

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.