Results 11 to 20 of about 2,252,336 (338)
A Survey on Metaverse: Fundamentals, Security, and Privacy [PDF]
IEEE Communications Surveys and Tutorials, 2022 Metaverse, as an evolving paradigm of the next-generation Internet, aims to build a fully immersive, hyper spatiotemporal, and self-sustaining virtual shared space for humans to play, work, and socialize.
Yuntao Wang +6 more
semanticscholar +1 more source
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy [PDF]
Journal of Artificial Intelligence Research, 2023 Machine Learning (ML) models are ubiquitous in real-world applications and are a constant focus of research. Modern ML models have become more complex, deeper, and harder to reason about.
N. Ponomareva +8 more
semanticscholar +1 more source
Deep Learning with Differential Privacy [PDF]
Conference on Computer and Communications Security, 2016 Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may be crowdsourced and contain sensitive information.
Martín Abadi +6 more
semanticscholar +1 more source
Knowledge Unlearning for Mitigating Privacy Risks in Language Models [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities.
Joel Jang +6 more
semanticscholar +1 more source
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2018 This position paper observes how different technical and normative conceptions of privacy have evolved in parallel and describes the practical challenges that these divergent approaches pose. Notably, past technologies relied on intuitive, heuristic understandings of privacy that have since been shown not to satisfy expectations for privacy protection.
Kobbi Nissim, Alexandra Wood
openaire +3 more sources
Multi-step Jailbreaking Privacy Attacks on ChatGPT [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from LLMs, it is still
Haoran Li +5 more
semanticscholar +1 more source
Federated Learning With Differential Privacy: Algorithms and Performance Analysis [PDF]
IEEE Transactions on Information Forensics and Security, 2019 Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving clients’ private data from being exposed to adversaries.
Kang Wei +8 more
semanticscholar +1 more source
New Program Abstractions for Privacy [PDF]
, 2020 Static program analysis, once seen primarily as a tool for optimising programs, is now increasingly important as a means to provide quality guarantees about programs. One measure of quality is the extent to which programs respect the privacy of user data.
C Dwork +5 more
core +1 more source
What Does it Mean for a Language Model to Preserve Privacy? [PDF]
Conference on Fairness, Accountability and Transparency, 2022 Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present in their ...
Hannah Brown +4 more
semanticscholar +1 more source
Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives
Cybersecurity, 2022 Empirical attacks on Federated Learning (FL) systems indicate that FL is fraught with numerous attack surfaces throughout the FL execution. These attacks can not only cause models to fail in specific tasks, but also infer private information.
Pengrui Liu, Xiangrui Xu, Wei Wang
doaj +1 more source