Claim Missing Document
Check
Articles

Found 5 Documents
Search

Comparative study of predictive models for hoax and disinformation detection in indonesian news Adiati, Nadia Paramita Retno; Priambodo, Dimas Febriyan; Girinoto, Girinoto; Indarjani, Santi; Rizal, Akhmad; Prayoga, Arga; Beatrix, Yehezikha
International Journal of Advances in Intelligent Informatics Vol 10, No 3 (2024): August 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v10i3.878

Abstract

Along with the times, false information easily spreads, including in Indonesia.  In Press Release No.485/HM/KOMINFO/12/2021 the Ministry of Communication and Information has cut off access to 565,449 negative content and published 1,773 clarifications on hoax and disinformation content. Research has been carried out regarding this matter, but it is necessary to classify fake news into disinformation and hoaxes. This study presents a comparison between our proposed model, which is an ensemble of shallow learning predictive models, namely Random Forest, Passive Aggressive Classifier, and Cosine Similarity, and the deep learning model that uses BERT-Indo for classification. Both models are trained using equivalent datasets, which contain 8757 news, consisting of 3000 valid news, 3000 hoax news, and 2757 disinformation news. These news were obtained from websites such as CNN, Kompas, Detik, Kominfo, Temanggung Mediacenter, Hoaxdb Aceh, Turnback Hoax, and Antara, which were then cleaned from all unnecessary substances, such as punctuation marks, numbers, Unicode, stopwords, and suffixes using the Sastrawi library. At the benchmarking stage, the shallow learning model is evaluated to increase accuracy by applying ensemble learning combined using hard voting.  This results in higher values, with an accuracy of 98.125%, precision of 98.2%, F-1 score of 98.1%, and recall of 98.1%, compared to the BERT-Indo model which only achieved 96.918% accuracy, 96.069% precision, 96.937% F-1 score, and 96.882% recall. Based on the accuracy value, shallow learning model is superior to deep learning model.  This machine learning model is expected to be used to combat the spread of hoaxes and disinformation in Indonesian news. Additionally, with this research, false news can be classified in more detail, both as hoaxes and disinformation
Serangan Second Preimage pada Skema Fungsi Hash Modifikasi Lin et al. Berbasis Algoritma SmallPresent[8] Kaloka, Fadhillah Novita; Adiati, Nadia Paramita Retno
Info Kripto Vol 18 No 3 (2024)
Publisher : Politeknik Siber dan Sandi Negara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56706/ik.v18i3.105

Abstract

Skema modifikasi Lin et al. merupakan skema Message Authentication Code (MAC) berbasis block cipher hasil modifikasi dari skema Lin et al. Perbedaan yang terdapat pada skema modifikasi Lin et al. dengan skema yang sebelumnya adalah adanya penambahan nilai salt, counter serta perubahan input pesan yang semula sepanjang  menjadi . Serangan second preimage dapat dilakukan menggunakan beberapa metode, diantaranya metode Jia et al. dan metode Liu et al. Pada penelitian ini dilakukan serangan second preimage dengan menggunakan metode Jia et al. dan Liu et al. Pencarian pesan second preimage dengan metode Jia et al. dilakukan dengan membangkitkan modifikasi pesan sebanyak  dan ditemukan pesan second preimage. Pada metode Liu et al. tidak didapatkan pesan second preimage karena pada serangan second preimage metode Liu et al. terdapat beberapa tahapan yaitu pencarian pesan fixed point, perluasan pesan serta pencarian pesan second preimage. Pada tahap pencarian pesan fixed point tidak ditemukan pesan yang memenuhi syarat sehingga tahap berikutnya tidak dapat dilakukan.
Implementasi DSA dengan SHA-512 pada Citra Digital Menggunakan Metode Reversible Image Steganography berbasis PVO Savitri, Arildha Rahma; Adiati, Nadia Paramita Retno; Barmawi, Ari Moesriami
Info Kripto Vol 19 No 2 (2025)
Publisher : Politeknik Siber dan Sandi Negara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56706/ik.v19i2.129

Abstract

Distribusi data digital melalui media elektronik rentan terhadap berbagai ancaman keamanan. Untuk menjamin keamanan transmisi, kriptografi digunakan sebagai mekanisme proteksi, tanda tangan digital digunakan untuk memastikan integritas dan otentikasi, sementara steganografi mencegah nilai tanda tangan dikirim secara terpisah. Penelitian ini mengimplementasikan Digital Signature Algorithm (DSA) dengan SHA-512 pada citra digital menggunakan metode reversible image steganography berbasis Pixel Value Ordering (PVO). Keunikan penelitian ini terletak pada pemanfaatan algoritma Scale Invariant Feature Transform (SIFT) untuk mengekstraksi fitur citra sebelum proses hashing, sehingga tanda tangan digital yang dihasilkan lebih tahan terhadap variasi citra. Proses meliputi pembangkitan kunci DSA, ekstraksi fitur citra, hashing dengan SHA-512, penandatanganan digital, serta penyisipan tanda tangan ke dalam citra menggunakan PVO. Hasil penelitian menunjukkan bahwa DSA dan SHA-512 dapat diimplementasikan pada citra digital baik jenis Grayscale ataupun RGB tanpa batasan ukuran pixel serta menunjukkan nilai signature yang disembunyikan tidak menyebabkan perubahan apapun terhadap cover-image. Hasil evaluasi performa dan analisis uji ketahanan metode steganografi PVO pada penelitian ini menunjukkan hasil Detection Rate, BPP, MSE, dan PSNR yang cukup baik.
Mathematics in Cryptography and Its Applications in Cybersecurity Isnaini, Uha; Qomariasih, Nurul; Amiruddin, Amiruddin; Tantrawan, Made; Arizal, Arizal; Ernanto, Iwan; Adiati, Nadia Paramita Retno; Indarsih, Indarsih; Yasa, Ray Novita; Wijayanti, Indah Emilia; Indarjani, Santi; Salmah, Salmah; Ulfa, Septia; Hartanto, Ari Dwi; Amelia, Fetty
Jurnal Pengabdian kepada Masyarakat (Indonesian Journal of Community Engagement) Vol 11, No 4 (2025): December
Publisher : Direktorat Pengabdian kepada Masyarakat Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jpkm.101525

Abstract

The growing prevalence of cyber threats and attacks poses significant risks to the security of personal data and the integrity of sensitive information worldwide. Cryptography plays a vital role in establishing strong cybersecurity defenses, and the development of robust cryptographic algorithms is essential for protecting data against cyber-attacks. This workshop aimed to enhance participants’ understanding of the mathematical foundations of cryptographic algorithms and equip them with practical skills to identify and mitigate cyber threats. It also introduced innovative educational tools, including an Augmented Reality (AR) application for teaching classical cryptography and a Game-Based URL Phishing Education application. A total of 110 participants attended and completed the pre-test. The post-test measured knowledge gained during the workshop, and an accompanying survey gathered feedback on its effectiveness and identified areas for improvement. Overall, the workshop successfully achieved its objectives by educating participants on cryptography in the Internet of Things (IoT), increasing awareness of social engineering, introducing cryptographic tools from ancient to modern times, and exploring the principles of quantum cryptography.
MATHEMATICAL ANALYSIS OF QC-MDPC STRUCTURES IN BIKE V5.2 POST-QUANTUM KEY ENCAPSULATION SCHEME Rosa, Rosa; Carita, Sa'aadah Sajjana; Adiati, Nadia Paramita Retno; Rosdiana, Sri
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol20iss2pp1061-1076

Abstract

The security of the BIKE scheme depends on a complex mathematical structure built upon QC-MDPC codes. This scheme is constructed using the Niederreiter framework and the application of transformation. Its security is based on the complexity of two main mathematical problems: the QCSD Problem and the QCCF Problem. The BIKE v5.2 scheme is the latest version of this scheme. This study aims to mathematically analyze the characteristics forming the BIKE v5.2, focusing on QC-MDPC codes, the Niederreiter framework, and the transformation, as well as the QCSD and QCCF problems. The method used in this study is a systematic literature review combined with theoretical analysis. The study highlights how the interplay of these three components forms a rational and resilient design. Although the BIKE v5.2 scheme was not selected for standardization by NIST, it is still capable of producing an efficient, secure, and relevant KEM for post-quantum cryptography. Through mathematical analysis of the QC-MDPC construction, the formulation of the complex computational problems QCCF and QCSD, and the rational design of the Niederreiter framework with the transformation, this study demonstrates that BIKE has a strong security foundation and resistance to both classical and quantum attacks.