Tag Archive for: Detection

Bitdefender unveils App Anomaly Detection to detect malicious activity in Android apps


Bitdefender has unveiled App Anomaly Detection, the real-time, behavior-based protection layer available now in Bitdefender Mobile Security for Android, that continuously detects anomalous and malicious behavior in Android applications as it emerges.

The number of malicious and compromised Android applications available for download in popular app stores continues to grow as cybercriminal groups increasingly leverage the malware as a service (MaaS) model.

Bitdefender research identified dozens of Android applications totaling millions of downloads in the Google Play store in the last year alone that turned malicious after users installed them, with some acting as delivery mechanisms for mobile banking trojans that steal users’ login credentials.

Bitdefender App Anomaly Detection is a technology integrated into the Bitdefender Malware Scanner to provide an additional layer of protection by continuously monitoring and detecting any malicious behaviors and alerting the user if suspicious activities are identified.

Designed to help safeguard Android mobile users’ data, financial assets, and identities from fake or malicious applications, App Anomaly Detection protects users from known and unknown (zero-day) attacks that result in financial loss, account takeover, and identity fraud.

Other anti-malware solutions for Android, currently available on the market, use signature-based detection, that cybercriminals could evade by designing their mobile applications to only manifest malicious behaviors when certain conditions are met, or after a period of days or weeks after they are first downloaded.

Bitdefender App Anomaly Detection uses a combination of machine learning models, real-time behavior scanning, reputation systems, and other data points to continuously monitor and detect the moment an application turns from benign to malicious.

In this way, Bitdefender App Anomaly Detection protects users even when they have unknowingly installed a dangerous app that runs dormant for a period of time or a seemingly trusted app that breaks its functionality and turns rogue – all with minimal impact on battery life.

“Cybercriminals exploit users’ inherent trust of popular…

Source…

Malware Taps Generative AI to Rewrite Code, Avoid Detection


Artificial Intelligence & Machine Learning
,
Cybercrime
,
Events

Mikko Hypponen Talks GPT-Enhanced Malware, Russian Cyber Operations and More

Mikko Hyppönen, chief research officer, WithSecure

Finnish cybersecurity expert Mikko Hyppönen recently received an email he wasn’t expecting: A malware developer sent him a copy of “LL Morpher,” a brand-new virus he’d written, which uses OpenAI’s GPT large language models.

See Also: Live Webinar | Education Cybersecurity Best Practices: Devices, Ransomware, Budgets and Resources


“It’s the first malware we’ve ever seen which uses GPT to rewrite its code,” said Hyppönen, who’s chief research officer at WithSecure, of the worm, which is written in Python and designed to infect Python files on a victim’s system. Instead of copying its functions into the infected file, the malware uses an API key to call GPT and give it English-language instructions about the malicious functionality it wants to be created.


“It calls GPT to write the code for it, which means every time it’s different, and it will be trivial to modify to write it in any other language,” Hyppönen said. “The whole AI thing right now feels exciting and scary at the same time.”


Thus far, this piece of malware is more proof-of-concept than actual threat, in that it’s available via GitHub, and for now could be contained by blocking the API key. Even so, Hyppönen says it should…

Source…

How is artificial intelligence used in fraud detection?


How can artificial intelligence help detect fraud?

Artificial Intelligence can play a crucial role in fraud management by detecting and preventing fraudulent activities.

The global average rate of losses caused by fraud for the last two decades represents 6.05% of the gross domestic product. Additionally, companies have reported that cyber breaches have caused financial damages equaling 3% to 10% of their revenue. Moreover, global digital fraud losses are projected to exceed $343 billion between 2023 and 2027.

Given the estimated amounts, it is a crucial question for any organization to build up an efficient fraud management system. Fraud management is identifying, preventing, detecting and responding to fraudulent activities within an organization.

Artificial intelligence (AI) has a significant role in fraud management. AI technologies, such as machine learning (ML) algorithms, can analyze large amounts of data and detect patterns and anomalies that may indicate fraudulent activities. AI-powered fraud management systems can identify and prevent various types of fraud, such as payment fraud, identity theft or phishing attacks. They can also adapt and learn from new fraud patterns and trends, improving their detection over time.

AI-based solutions can also integrate with other security systems, such as identity verification and biometric authentication, to provide a more comprehensive approach to fraud prevention.

How can machine learning algorithms help in fraud detection and prevention?

Machine learning algorithms are designed to recognize patterns based on a large amount of data, which can be leveraged to identify fraudulent activities.

AI refers to technologies that can perform tasks requiring human intelligence, such as analyzing data or understanding and responding to human language. They are designed to recognize patterns and make predictions in real time. AI algorithms are often a combination of different ML models.

ML is a subset of AI; it uses algorithms to analyze large amounts of data to enable systems to learn autonomously. The more data ML algorithms are exposed to, the better they perform over time. The two main approaches of ML are supervised machine learning…

Source…

Trustport Internet Security 2013 beta test and review