Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators

• URL: http://arxiv.org/abs/2402.01708v2
• Date: Wed, 15 May 2024 15:26:42 GMT
• Title: Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators
• Authors: Wiebke Hutiri, Oresiti Papakyriakopoulos, Alice Xiang,
• Abstract summary: We analyse speech generation incidents to study how patterns of specific harms arise. We propose a conceptual framework for modelling pathways to ethical and safety harms of AI. Our relational approach captures the complexity of risks and harms in sociotechnical AI systems.
• Score: 2.500481442438427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid and wide-scale adoption of AI to generate human speech poses a range of significant ethical and safety risks to society that need to be addressed. For example, a growing number of speech generation incidents are associated with swatting attacks in the United States, where anonymous perpetrators create synthetic voices that call police officers to close down schools and hospitals, or to violently gain access to innocent citizens' homes. Incidents like this demonstrate that multimodal generative AI risks and harms do not exist in isolation, but arise from the interactions of multiple stakeholders and technical AI systems. In this paper we analyse speech generation incidents to study how patterns of specific harms arise. We find that specific harms can be categorised according to the exposure of affected individuals, that is to say whether they are a subject of, interact with, suffer due to, or are excluded from speech generation systems. Similarly, specific harms are also a consequence of the motives of the creators and deployers of the systems. Based on these insights we propose a conceptual framework for modelling pathways to ethical and safety harms of AI, which we use to develop a taxonomy of harms of speech generators. Our relational approach captures the complexity of risks and harms in sociotechnical AI systems, and yields a taxonomy that can support appropriate policy interventions and decision making for the responsible development and release of speech generation models.

Related papers

• "My Replika Cheated on Me and She Liked It": A Taxonomy of Algorithmic Harms in Human-AI Relationships [17.5741039825938]
  We identify six categories of harmful behaviors exhibited by the AI companion Replika. The AI contributes to these harms through four distinct roles: perpetrator, instigator, facilitator, and enabler.
  arXiv  Detail & Related papers  (2024-10-26T09:18:17Z)
• Mapping the individual, social, and biospheric impacts of Foundation Models [0.39843531413098965]
  This paper offers a critical framework to account for the social, political, and environmental dimensions of foundation models and generative AI. We identify 14 categories of risks and harms and map them according to their individual, social, and biospheric impacts.
  arXiv  Detail & Related papers  (2024-07-24T10:05:40Z)
• Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights [50.89022445197919]
  We propose a speech-specific risk taxonomy, covering 8 risk categories under hostility (malicious sarcasm and threats), malicious imitation (age, gender, ethnicity), and stereotypical biases (age, gender, ethnicity) Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk.
  arXiv  Detail & Related papers  (2024-06-25T10:08:45Z)
• Near to Mid-term Risks and Opportunities of Open-Source Generative AI [94.06233419171016]
  Applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic changes has triggered a lively debate about potential risks and resulted in calls for tighter regulation. This regulation is likely to put at risk the budding field of open-source Generative AI.
  arXiv  Detail & Related papers  (2024-04-25T21:14:24Z)
• A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI [19.675489660806942]
  Generative AI presents a new risk profile of persuasion due to reciprocal exchange and prolonged interactions. This has led to growing concerns about harms from AI persuasion and how they can be mitigated. Existing harm mitigation approaches prioritise harms from the outcome of persuasion over harms from the process of persuasion.
  arXiv  Detail & Related papers  (2024-04-23T14:07:20Z)
• Where's the Liability in Harmful AI Speech? [42.97651263209725]
  Machine learning practitioners regularly "red team" models to identify problematic speech. We examine three liability regimes, tying them to common examples of red-teamed model behaviors. We argue that AI should not be categorically immune from liability in these scenarios.
  arXiv  Detail & Related papers  (2023-08-09T00:13:00Z)
• Mitigating Covertly Unsafe Text within Natural Language Systems [55.26364166702625]
  Uncontrolled systems may generate recommendations that lead to injury or life-threatening consequences. In this paper, we distinguish types of text that can lead to physical harm and establish one particularly underexplored category: covertly unsafe text.
  arXiv  Detail & Related papers  (2022-10-17T17:59:49Z)
• Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey [50.58063811745676]
  This work provides a survey of practical methods for addressing potential threats and societal harms from language generation models. We draw on several prior works' of language model risks to present a structured overview of strategies for detecting and ameliorating different kinds of risks/harms of language generators.
  arXiv  Detail & Related papers  (2022-10-14T10:43:39Z)
• Adversarial Interaction Attack: Fooling AI to Misinterpret Human Intentions [46.87576410532481]
  We show that, despite their current huge success, deep learning based AI systems can be easily fooled by subtle adversarial noise. Based on a case study of skeleton-based human interactions, we propose a novel adversarial attack on interactions. Our study highlights potential risks in the interaction loop with AI and humans, which need to be carefully addressed when deploying AI systems in safety-critical applications.
  arXiv  Detail & Related papers  (2021-01-17T16:23:20Z)
• Overcoming Failures of Imagination in AI Infused System Development and Deployment [71.9309995623067]
  NeurIPS 2020 requested that research paper submissions include impact statements on "potential nefarious uses and the consequences of failure" We argue that frameworks of harms must be context-aware and consider a wider range of potential stakeholders, system affordances, as well as viable proxies for assessing harms in the widest sense.
  arXiv  Detail & Related papers  (2020-11-26T18:09:52Z)

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.