Concrete Safety for ML Problems: System Safety for ML Development and Assessment

• URL: http://arxiv.org/abs/2302.02972v1
• Date: Mon, 6 Feb 2023 18:02:07 GMT
• Title: Concrete Safety for ML Problems: System Safety for ML Development and Assessment
• Authors: Edgar W. Jatho and Logan O. Mailloux and Eugene D. Williams and Patrick McClure and Joshua A. Kroll
• Abstract summary: Concerns of trustworthiness, unintended social harms, and unacceptable social and ethical violations undermine the promise of ML advancements. Systems safety engineering is an established discipline with a proven track record of identifying and managing risks even in high-complexity sociotechnical systems.
• Score: 0.758305251912708
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Many stakeholders struggle to make reliances on ML-driven systems due to the risk of harm these systems may cause. Concerns of trustworthiness, unintended social harms, and unacceptable social and ethical violations undermine the promise of ML advancements. Moreover, such risks in complex ML-driven systems present a special challenge as they are often difficult to foresee, arising over periods of time, across populations, and at scale. These risks often arise not from poor ML development decisions or low performance directly but rather emerge through the interactions amongst ML development choices, the context of model use, environmental factors, and the effects of a model on its target. Systems safety engineering is an established discipline with a proven track record of identifying and managing risks even in high-complexity sociotechnical systems. In this work, we apply a state-of-the-art systems safety approach to concrete applications of ML with notable social and ethical risks to demonstrate a systematic means for meeting the assurance requirements needed to argue for safe and trustworthy ML in sociotechnical systems.

Related papers

• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• Cross-Modality Safety Alignment [73.8765529028288]
  We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment. To empirically investigate this problem, we developed the SIUO, a cross-modality benchmark encompassing 9 critical safety domains, such as self-harm, illegal activities, and privacy violations. Our findings reveal substantial safety vulnerabilities in both closed- and open-source LVLMs, underscoring the inadequacy of current models to reliably interpret and respond to complex, real-world scenarios.
  arXiv  Detail & Related papers  (2024-06-21T16:14:15Z)
• Prioritizing Safeguarding Over Autonomy: Risks of LLM Agents for Science [65.77763092833348]
  Intelligent agents powered by large language models (LLMs) have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these agents also introduce novel vulnerabilities that demand careful consideration for safety. This paper conducts a thorough examination of vulnerabilities in LLM-based agents within scientific domains, shedding light on potential risks associated with their misuse and emphasizing the need for safety measures.
  arXiv  Detail & Related papers  (2024-02-06T18:54:07Z)
• RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization [49.26510528455664]
  We introduce the Risk-sensitive Individual-Global-Max (RIGM) principle as a generalization of the Individual-Global-Max (IGM) and Distributional IGM (DIGM) principles. We show that RiskQ can obtain promising performance through extensive experiments.
  arXiv  Detail & Related papers  (2023-11-03T07:18:36Z)
• 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)
• System Safety Engineering for Social and Ethical ML Risks: A Case Study [0.5249805590164902]
  Governments, industry, and academia have undertaken efforts to identify and mitigate harms in ML-driven systems. Existing approaches are largely disjointed, ad-hoc and of unknown effectiveness. We focus in particular on how this analysis can extend to identifying social and ethical risks and developing concrete design-level controls to mitigate them.
  arXiv  Detail & Related papers  (2022-11-08T22:58:58Z)
• From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML [8.411124873373172]
  Inappropriate design and deployment of machine learning (ML) systems leads to negative downstream social and ethical impact for users, society and the environment. Despite the growing need to regulate ML systems, current processes for assessing and mitigating risks are disjointed and inconsistent.
  arXiv  Detail & Related papers  (2022-10-06T00:09:06Z)
• The Risks of Machine Learning Systems [11.105884571838818]
  A system's overall risk is influenced by its direct and indirect effects. Existing frameworks for ML risk/impact assessment often address an abstract notion of risk or do not concretize this dependence. First-order risks stem from aspects of the ML system, while second-order risks stem from the consequences of first-order risks.
  arXiv  Detail & Related papers  (2022-04-21T02:42:10Z)
• Unsolved Problems in ML Safety [45.82027272958549]
  We present four problems ready for research, namely withstanding hazards, identifying hazards, steering ML systems, and reducing risks to how ML systems are handled. We clarify each problem's motivation and provide concrete research directions.
  arXiv  Detail & Related papers  (2021-09-28T17:59:36Z)
• SoK: Machine Learning Governance [16.36671448193025]
  We develop the concept of ML governance to balance such benefits and risks. We use identities to hold principals accountable for failures of ML systems. We highlight the need for techniques that allow a model owner to manage the life cycle of their system.
  arXiv  Detail & Related papers  (2021-09-20T17:56:22Z)
• Towards a Robust and Trustworthy Machine Learning System Development [0.09236074230806578]
  We present our recent survey on the state-of-the-art ML trustworthiness and technologies from a security engineering perspective. We then push our studies forward above and beyond a survey by describing a metamodel we created that represents the body of knowledge in a standard and visualized way for ML practitioners. We propose future research directions motivated by our findings to advance the development of robust and trustworthy ML systems.
  arXiv  Detail & Related papers  (2021-01-08T14:43:58Z)

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.