AAAI2023「Are Transformers Effective for Time Series Forecasting?」と、HuggingFace「Yes, Transformers are Effective for Time Series Forecasting (+ Autoformer)」の紹介です。
AAAI2023「Are Transformers Effective for Time Series Forecasting?」と、HuggingFace「Yes, Transformers are Effective for Time Series Forecasting (+ Autoformer)」の紹介です。
Privacy Protectin Models and Defamation caused by k-anonymityHiroshi Nakagawa
Introduction of Privacy Protection Mathematical Models are the topics of this slide. The Models explained are 1) Private Information Retrieval, 2) IR with Homomorphic Encryption, 3) k-anonymity, 4) l-diversity, and finally 5) Defamation caused by k-Anonymity
In order to protect privacy, many technologies are used for various purposes. This slide is an introductory overview of these technologies for each purpose, including private information retrieval, secure computation, pseudonymization, anonymization and differential privacy.
Japanese Personal Information Protection Act (PIPA) was passed the diet in Sep.2015. De-identified Information is introduced. It is the data anonymized enough not to de-anonymized easily. It is permitted to freely use without the consent of data subject. Notice that pseudonymized is not regarded as De-identified Information. Boarder line between pseudonymized and anonymized is a critical issue. I discuss this topic in this slide.
Problems in Technology to Use Anonymized Personal DataHiroshi Nakagawa
Privacy is a big issue these days. Legally, EU data protection directive will be revised, Google was defeated in EU court and forced to erase data link uopn user's request.
However, we are facing various technical problems to be solved even if limiting to anonyumisation or k-anonymity. In this slide, we describe three of these problmes.
This slide shows (1) AI and Accountability , (2) AI Ethics, (2) Privacy Protection. Several AI ethics documents such as IEEE EAD, EC-HELG Ethics Guideline for Trustworthy AI, Social Principles of Human-Centric AI(Japan), focus on AI's transparency, accountability and trust. We follow the discussions of these documents around the above (1),(2) and (3) topics.
What is Accountability of AI? We answer to this question by clarifying responsibility, explainability and liability of limited autonomous AI with several bright and dark real examples.
Then we move to the concept of "Trust " which is of not limited to single AI system but group AI ‘s behavior.
K-anonymization has been regarded as a great method to make a bad person indistinguishable among k people whose quasi identifiers are same.
It, unfortunately, has a problematic side effect of defamation. In this case, defamation means the case where other good k-1 people are suspected as a bad person because both of a bad person and good people have the same quasi identifiers because of k-anonymization. This slide shows a mathematical model of defamation and proposes an algorithm which minimizes the probability of defamation.
Social Effects by the Singularity -Pre-Singularity Era-Hiroshi Nakagawa
Contents:
Stance of scientists community against Pre-Singularity problems
Amplification vs. Replacement
AI takes over jobs
Boarder line between amplification and replacement
Autonomous driver: trolley problem
The right to be forgotten
Towards black box
Responsibility
Vulnerability of financial dealing system made of many AI agent traders connected via internet
AI and weapon
Filter bubble phenomena
Analogy: Selfish gene
AI and privacy
The right to be forgotten, Profiling and Don’t Track
Feeling of friendliness to android
Again self conscious and identity