Hasil Pencarian  ::  Simpan CSV :: Kembali

"Tulisan ini menganalisis pengaturan pemeriksaan algoritma pada sistem kecerdasan artifisial (AI) dalam regulasi penyelenggaraan sistem elektronik, pelindungan hak kekayaan intelektual, pelindungan konsumen, pelindungan data pribadi, dan hukum perjanjian di Indonesia. Tulisan ini disusun dengan metode doktrinal yang dilakukan melalui analisis terhadap norma-norma hukum terkait pemeriksaan algoritma sistem AI di Indonesia. Tulisan ini dilatarbelakangi bahwa penyelenggaraan AI memiliki sejumlah risiko yang membahayakan kesehatan, keselamatan, dan hak-hak fundamental. Oleh karena itu, perlu ada langkah mitigasi terhadap risiko-risiko tersebut, salah satunya melalui pemeriksaan algoritma sistem AI. Pemeriksaan algoritma pada sistem AI merupakan serangkaian pemeriksaan terhadap sistem internal AI yang bertujuan untuk memitigasi risiko serta memastikan akuntabilitas, transparansi, dan keamanan dalam penyelenggaraan AI. Hasil temuan tulisan ini menunjukkan bahwa sejumlah regulasi di Indonesia memungkinkan pemeriksaan algoritma sistem AI dalam sejumlah variasi. Namun, pengaturannya masih sangat bersifat umum dan belum ada kejelasan terkait tujuan, mekanisme, dan pertanggungjawaban dalam pelaksanaannya. Dengan membandingkan pengaturan pemeriksaan algoritma sistem AI di Uni Eropa dan Tiongkok, tulisan ini menyarankan bahwa Indonesia perlu mengatur pemeriksaan algoritma sistem AI secara lebih spesifik disertai dengan ketentuan yang memastikan pelindungan hak dan kepentingan penyelenggara AI atas sistemnya, terutama hak kekayaan intelektual.

---

This paper analyzes the provisions governing algorithm auditing in artificial intelligence (AI) systems under Indonesian regulations on electronic systems, intellectual property rights protection, consumer protection, personal data protection, and contract law. This paper is grounded in a doctrinal method by analyzing legal norms governing the auditing of AI algorithms in Indonesia. This paper is based on the fact that the deployment of AI poses various risks which threaten health, safety, and fundamental rights. Therefore, mitigation measures are necessary to address these risks, one of which is AI algorithm auditing. Algorithm auditing in AI systems is the process of checking internal AI systems to mitigate risks and ensure accountability, transparency, and security in AI deployment. The research findings show that certain regulations in Indonesia permit AI algorithm auditing in several variations. However, those regulations are still very broad and lack clarity regarding the objectives, mechanisms, and accountability in their implementation. By comparing the regulations on AI algorithm auditing in the European Union and China, this paper concludes that Indonesia needs to regulate AI algorithm auditing more specifically, accompanied by provisions that ensure the protection of the rights and interests of AI providers over their systems, especially intellectual property rights.

"

"Tulisan ini menganalisis cakupan kewajiban penyelenggaraan sistem elektronik secara aman terhadap AI berdasarkan ketentuan UU ITE. Tulisan ini disusun dengan menggunakan metode penelitian doktrinal. AI karena secara konstruksi sistemnya termasuk pada sistem elektronik. Saat ini, Indonesia belum memiliki regulasi yang spesifik mengatur mengenai AI, sehingga ketentuan mengenai keamanan AI juga merujuk kembali pada ketentuan keamanan sistem elektronik. Berbeda dengan Uni Eropa yang telah meregulasi sistem AI dan juga keamanan sistem AI melalui EU AI Act. Uni Eropa telah mengatur mengenai apa yang dimaksud dengan sistem AI dan subjek-subjek hukum terkait AI, seperti AI provider, AI deployer, dan AI office, serta satu ketentuan pengujian, yaitu testing in real-world conditions. Dalam konstruksinya AI sebagai sistem elektronik, hal tersebut merupakan solusi hukum di Indonesia yang dapat digunakan untuk menjamin keamanan sistem AI. Akan tetapi, definisi sistem elektronik dalam Pasal 1 angka 5 UU ITE belum mencakup sistem AI secara penuh. Pendefinisian AI di Indonesia masih merujuk pada suatu sistem prosedur elektronik dan tidak merujuk tentang kemampuan AI dalam beroperasi. Perbandingan kewajiban para subjek hukum terkait keamanan telah terlihat dari subjek hukum yang telah didefinisikan secara jelas di Uni Eropa. Kewajiban berdasarkan kontribusi atas sistem AI atas risiko dan modelnya, sehingga dibebankan lebih banyak kepada AI provider dan AI deployer yang termasuk dalam subjek yang mengoperasikan sistem AI. EU AI Act yang memfasilitasi pengujian sistem AI melalui testing in real-world conditions belum diadopsi dalam sistem hukum Indonesia. Belum adanya dukungan regulasi yang memadai untuk tahap pengujian sistem AI di Indonesia, tetapi terdapat ketentuan uji kelaikan yang memiliki kemiripan terbatas dengan konsep testing in real-world conditions.

---

This paper analyzes the scope of obligations to operate electronic system securely with regard to AI based on the provisions of the ITE Law. This paper employs doctrinal legal research. AI is included in electronic system due to its structural design. Currently, Indonesia does not have specific regulations governing AI, so provisions regarding AI security also refer back to provisions on electronic system security. This contrasts with the European Union, which has regulated AI system and AI system security through the EU AI Act. The EU has defined what constitutes an AI system and the legal entities related to AI, such as AI providers, AI deployers, and AI offices, as well as a testing requirement, namely testing in real-world conditions. Given that AI is constructed as an electronic system, this could serve as a legal solution in Indonesia to ensure AI system security. However, the definition of electronic system in Article 1(5) of the ITE Law does not fully encompass AI system. The definition of AI in Indonesia still refers to an electronic procedure system and does not address AI's operational capabilities. A comparison of the obligations of legal entities related to security is evident from the clearly defined legal entities in the European Union. Obligations based on contributions to AI system in terms of risk and models are therefore placed more heavily on AI providers and AI deployers who are included in the subjects operating AI system. The EU AI Act, which facilitates the testing of AI system through testing in real-world conditions, has not yet been adopted in the Indonesian legal system. There is currently no adequate regulatory support for the testing phase of AI system in Indonesia, but there are provisions for suitability testing that have limited similarities with the concept of testing in real-world conditions."

"Algorithms are a fundamental building block of artificial intelligence - and, increasingly, society - but our legal institutions have largely failed to recognize or respond to this reality. The Cambridge Handbook of the Law of Algorithms, which features contributions from US, EU, and Asian legal scholars, discusses the specific challenges algorithms pose not only to current law, but also - as algorithms replace people as decision makers - to the foundations of society itself. The work includes wide coverage of the law as it relates to algorithms, with chapters analyzing how human biases have crept into algorithmic decision-making about who receives housing or credit, the length of sentences for defendants convicted of crimes, and many other decisions that impact constitutionally protected groups. Other issues covered in the work include the impact of algorithms on the law of free speech, intellectual property, and commercial and human rights law."

"Pencarian dokumen hukum yang relevan dan efisien merupakan kebutuhan penting bagi praktisi hukum, akademisi, dan masyarakat umum di Indonesia. Penelitian ini memperkenalkan Lexin, sebuah aplikasi web berbasis model Retrieval Augmented Generation (RAG) untuk mengolah sumber hukum di Indonesia. Dengan memanfaatkan teknologi seperti Elasticsearch untuk pencarian teks penuh dengan pengurutan dan penyaringan beserta GPT-4o Mini dari OpenAI sebagai model bahasa besar, aplikasi ini memberikan solusi inovatif untuk meningkatkan akurasi, relevansi, dan efisiensi pencarian dokumen hukum. Pengembangan Lexin mencakup integrasi antarmuka berbasis Next.js untuk frontend, FastAPI untuk backend, dan Elasticsearch sebagai penyimpanan dokumen hukum. Evaluasi dilakukan melalui User Acceptance Testing (UAT), System Usability Scale (SUS), User Experience Questionnaire (UEQ), dan pengujian beban menggunakan Locust. Hasil evaluasi menunjukkan bahwa frontend Lexin berhasil menawarkan antarmuka pengguna yang intuitif dan responsif. Evaluasi UAT menunjukkan tingkat kepuasan pengguna mencapai 93,4%, dengan umpan balik positif terkait kemudahan navigasi dan kecepatan akses fitur. Pengukuran SUS menghasilkan skor 81, yang berada dalam kategori ”Sangat Baik”, mengindikasikan aplikasi mudah dipahami dan digunakan oleh berbagai jenis pengguna. Evaluasi UEQ menunjukkan nilai tinggi pada dimensi efisiensi (1,8) dan atraktivitas (1,7), memperlihatkan desain antarmuka yang ramah pengguna dan fungsional. Di sisi backend, aplikasi menunjukkan performa yang baik dengan kemampuan menangani hingga 304 permintaan dalam 60 detik menggunakan 4 instance backend API, dengan rata-rata waktu respons sebesar 2.418 ms, turun 55% dibandingkan tanpa autoscaling. Kemampuan Elasticsearch dalam pencarian dokumen menunjukkan waktu respons rata-rata sebesar 94 ms pada beban rendah dan 894 ms pada beban tinggi. Secara keseluruhan, aplikasi ini berhasil memberikan solusi yang efisien untuk pencarian dan pengelolaan dokumen hukum, memenuhi kebutuhan pengguna dari berbagai latar belakang. Lexin diharapkan dapat menjadi alat yang bermanfaat dalam meningkatkan aksesibilitas informasi hukum di Indonesia.

---

Efficient and relevant legal document retrieval is a critical need for legal practitioners, academics, and the general public in Indonesia. This research introduces Lexin, a web application based on the Retrieval Augmented Generation (RAG) model to process Indonesian legal resources. By leveraging technologies such as Elasticsearch for full-text search with ranking and filtering capabilities, and OpenAI’s GPT-4o Mini as a large language model, the application provides an innovative solution to enhance the accuracy, relevance, and efficiency of legal document search. The development of Lexin integrates a Next.js-based frontend, FastAPI for the backend, and Elasticsearch as the repository for legal documents. Evaluation methods include User Acceptance Testing (UAT), the System Usability Scale (SUS), the User Experience Questionnaire (UEQ), and load testing using Locust. The evaluation results show that the Lexin frontend successfully offers an intuitive and responsive user interface. UAT evaluation results show a user satisfaction rate of 93.4%, with positive feedback on navigation ease and feature access speed. The SUS measurement yields a score of 81, categorized as ”Excellent,” indicating that the application is easy to understand and use by various types of users. UEQ evaluation demonstrates high scores in the dimensions of efficiency (1.8) and attractiveness (1.7), reflecting a user-friendly and functional interface design. On the backend side, the application shows robust performance, handling up to 304 requests within 60 seconds using 4 backend API instances, with an average response time of 2,418 msa 55% reduction compared to scenarios without autoscaling. Elasticsearch demonstrates an average response time of 94 ms under low load and 894 ms under high load conditions. Overall, this application successfully provides an efficient solution for legal document retrieval and management, addressing the needs of users from various backgrounds. Lexin is expected to serve as a valuable tool for improving the accessibility of legal information in Indonesia."