Magnet Forensics Launches Solution to Catch Criminals by Analyzing Chat Contexts with AI

This page was machine-translated and may differ from the original. View original

Magnet Forensics Launches Solution to Catch Criminals by Analyzing Chat Contexts with AI

Published2017.07.19 10:56

Launch of 'Magnet Axiom 1.1', a digital evidence collection and analysis solution
TrueCrypt, Full Disk Decryption to Recover Data from Encrypted Drives with BitLocker

Magnet Forensics today announced the release of a new version of its evidence collection and analysis solution, Magnet AXIOM. The newly released Magnet AXIOM 1.1 adds AI capabilities for chat analysis for the first time in the industry, and supports more powerful investigation tools and faster processing.

Magnet Axiom is a comprehensive digital evidence collection and analysis solution that collects data from smartphones and computers, examines evidence data, and provides results reports on a single platform. Currently, Magnet Forensics' Internet evidence analysis solutions are being used by over 3,200 customers in 92 countries around the world, including law enforcement, government, military, and corporate organizations. In Korea, the company's main customers include major law enforcement agencies, copyright-related organizations, public and corporate audit teams, law firms, and large corporations.

Key features of the enhanced Magnet Axiom 1.1 include: ▲Magnet AI, a new contextual analysis technology ▲Full disk decryption to recover encrypted drive data ▲Powerful filtering and tagging to enhance chat analysis ▲PST file export ▲Adding new evidence to existing case files, etc.

Adam Belsher, CEO of Magnet Forensics, said, “As devices like smartphones gain more storage, they become like PCs in our pockets, and criminals in particular are actively using them. Magnet Forensics is driven by a sense of mission to support more in-depth investigations, and we are particularly focused on developing technologies that enable our customers to more effectively deal with the explosion of data and the resource constraints required to sort through their backlog.”

Along with this, Axiom has improved processing and performance speed by about 30% while adding new artifacts (evidence of creation, data automatically generated by a system or application) and search regions. Specifically, Axiom’s processing process includes device image creation, keyword indexing, and the collection of all data collected from all devices into a case file, enabling investigators to quickly move from device processing to investigation.

Magnet also supports integration of third-party tools through Axiom, considering that digital forensics professionals use a variety of tools to acquire and examine data. Data from JTEG and Chip-off processes can be added to Axiom case files and examined using Axiom’s analysis tools. Recently, it has been integrated with the GriefEye product to analyze image and video files and detect child abuse and child pornography.

#AI

본 기사에 대한 정정·반론·추후보도 청구는 보도 청구 안내를, 그간 게재된 보도문은 정정·반론보도 모아보기를 참고해 주세요.

김자영 기자

All articles by this reporter

관련뉴스

ON Semiconductor Detects Hidden Leaks with Battery-Free Wireless Sensor

ON Semiconductor has developed a complete in-line vehicle production leak detection solution through collaboration with RFMicron. The Moisture Intrusion Detection System (RFM5126) uses battery-free, wireless sensors to detect leaks inside vehicles caused by improper assembly. The system employs moisture sensing sensors that integrate RFMicron's Magnus IC. ICs based on Magnus technology support battery-free wireless sensors provided by Smart Passive Sensors and SPS. Vehicle assembly is a complex process involving various materials, adhesives, component variations, and manual labor processes. Despite the automotive industry's efforts, minor leaks can be missed during various manual inspection procedures. However, when water enters the vehicle due to these leaks, it can cause mold growth on or potentially damage expensive electronic modules and components over time.

2017.05.10by 김자영 기자

Elastic equips Elastic Stack with machine learning capabilities

Elastic, a global open-source company that solves mission-critical data challenges in search, logging, and analytics using Elasticsearch and Elastic Stack, announced that it has introduced unsupervised machine learning capabilities for the first time in its Elastic 5.4 version. By integrating the machine learning capabilities of recently acquired Prelert into the Elastic Stack, customers can now leverage machine learning functionality without requiring complex specialized knowledge or additional development. Elastic's new machine learning features are equipped with time-series data solutions that automatically detect anomalies, efficiently perform root cause analysis, and reduce false positives in real-time applications. This technology is well-suited for businesses seeking to identify infrastructure technical issues, cyber attacks, and business problems in real time.

2017.05.12by 김자영 기자

How far should humans go in their efforts for artificial intelligence?

Digiceo released a report on the theme of "Evolution of Crowdsourcing Platforms for Artificial Intelligence." It stated that in the United States, the highest-earning workers are artificial intelligence engineers, machine learning engineers, and data scientists in that order, and that companies are actively engaged in developing algorithms for machine learning targeting unstructured data. The algorithms developed in this manner require extensive additional training to achieve desired results. Similarly, obtaining desired results in any given field depends on the quantity and quality of training data. Tens of millions of vast amounts of data must be individually classified by people, and results necessary for training must be entered manually.

2017.05.26by 김자영 기자

ST Microelectronics and NUS Establish Joint Research Center 'HELIX' for Edge AI

ST Microelectronics and the National University of Singapore have established the 'HELIX' joint research center aimed at implementing embedded AI in edge environments. Over a four-year period, the center will conduct research across the entire technology stack from algorithms to silicon, focusing on memory-centric architecture leveraging ST's 18nm FD-SOI technology and embedded PCM. The core objective is to implement intelligence directly in physical devices such as robots and drones while minimizing energy consumption.

2026.08.28by 배종인 기자

ams, 디지털 포토닉스로 휴머노이드 로봇 감각·소통 기능 지원

ams OSRAM이 디지털 포토닉스 기술을 활용해 휴머노이드 로봇의 감각·소통 기능을 강화하는 솔루션을 공개했다. dToF 센서, 광학식 힘 센서, 구조광 이미터 등으로 주변 환경 인식과 정밀 조작을 구현하며, EVIYOS·ALIYOS 플랫폼으로 LED 기반 비언어 소통을 지원한다. 시장조사에 따르면 휴머노이드 로봇 시장은 2025년 6억 달러에서 2035년 510억 달러로 성장할 전망이며, 로봇의 감각 능력 향상이 핵심 성장 동인으로 작용할 것으로 예상된다.

2026.08.27by 배종인 기자