Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives
- URL: http://arxiv.org/abs/2407.02027v1
- Date: Tue, 2 Jul 2024 07:49:48 GMT
- Title: Privacy Risks of General-Purpose AI Systems: A Foundation for Investigating Practitioner Perspectives
- Authors: Stephen Meisenbacher, Alexandra Klymenko, Patrick Gage Kelley, Sai Teja Peddinti, Kurt Thomas, Florian Matthes,
- Abstract summary: Powerful AI models have led to impressive leaps in performance across a wide range of tasks.
Privacy concerns have led to a wealth of literature covering various privacy risks and vulnerabilities of AI models.
We conduct a systematic review of these survey papers to provide a concise and usable overview of privacy risks in GPAIS.
- Score: 47.17703009473386
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The rise of powerful AI models, more formally $\textit{General-Purpose AI Systems}$ (GPAIS), has led to impressive leaps in performance across a wide range of tasks. At the same time, researchers and practitioners alike have raised a number of privacy concerns, resulting in a wealth of literature covering various privacy risks and vulnerabilities of AI models. Works surveying such risks provide differing focuses, leading to disparate sets of privacy risks with no clear unifying taxonomy. We conduct a systematic review of these survey papers to provide a concise and usable overview of privacy risks in GPAIS, as well as proposed mitigation strategies. The developed privacy framework strives to unify the identified privacy risks and mitigations at a technical level that is accessible to non-experts. This serves as the basis for a practitioner-focused interview study to assess technical stakeholder perceptions of privacy risks and mitigations in GPAIS.
Related papers
- Collection, usage and privacy of mobility data in the enterprise and public administrations [55.2480439325792]
Security measures such as anonymization are needed to protect individuals' privacy.
Within our study, we conducted expert interviews to gain insights into practices in the field.
We survey privacy-enhancing methods in use, which generally do not comply with state-of-the-art standards of differential privacy.
arXiv Detail & Related papers (2024-07-04T08:29:27Z) - Centering Policy and Practice: Research Gaps around Usable Differential Privacy [12.340264479496375]
We argue that while differential privacy is a clean formulation in theory, it poses significant challenges in practice.
To bridge the gaps between differential privacy's promises and its real-world usability, researchers and practitioners must work together.
arXiv Detail & Related papers (2024-06-17T21:32:30Z) - A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures [50.987594546912725]
Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations.
This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures.
arXiv Detail & Related papers (2024-03-31T12:44:48Z) - The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented
Generation (RAG) [56.67603627046346]
Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data.
In this work, we conduct empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems on leaking the private retrieval database.
arXiv Detail & Related papers (2024-02-23T18:35:15Z) - 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) - Open Government Data Programs and Information Privacy Concerns: A
Literature Review [0.0]
Findings suggest contradictions with Fair Information Practices, reidentification risks, conflicts with Open Government Data (OGD) value propositions, and smart city data practices are significant privacy concerns in the literature.
Proposed solutions include technical, legal, and procedural measures to mitigate privacy concerns.
arXiv Detail & Related papers (2023-12-14T16:03:49Z) - Security and Privacy on Generative Data in AIGC: A Survey [17.456578314457612]
We review the security and privacy on generative data in AIGC.
We reveal the successful experiences of state-of-the-art countermeasures in terms of the foundational properties of privacy, controllability, authenticity, and compliance.
arXiv Detail & Related papers (2023-09-18T02:35:24Z) - Technocracy, pseudoscience and performative compliance: the risks of
privacy risk assessments. Lessons from NIST's Privacy Risk Assessment
Methodology [0.0]
Privacy risk assessments have been touted as an objective, principled way to encourage organizations to implement privacy-by-design.
Existing guidelines and methods remain vague, and there is little empirical evidence on privacy harms.
We highlight the limitations and pitfalls of what is essentially a utilitarian and technocratic approach.
arXiv Detail & Related papers (2023-08-24T01:32:35Z) - Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment [100.1798289103163]
We present a detailed review of current practices and state-of-the-art methodologies in the field of differential privacy (DP)
Key points and high-level contents of the article were originated from the discussions from "Differential Privacy (DP): Challenges Towards the Next Frontier"
This article aims to provide a reference point for the algorithmic and design decisions within the realm of privacy, highlighting important challenges and potential research directions.
arXiv Detail & Related papers (2023-04-14T05:29:18Z) - Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future
Directions [23.778855805039438]
We provide a new taxonomy for privacy risks and protection methods in AVs.
We categorize privacy in AVs into three levels: individual, population, and proprietary.
arXiv Detail & Related papers (2022-09-08T20:16:21Z)
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.