Bank Creates Its Own AI To Identify & Disintegrate Malware

JPMorgan Chase is integrating Artificial Intelligence into its internal security systems to thwart malware infections within its own networks.
 
Machine-learning code predicts whether connections are legit or likely to result in a bad day for someone. The majority of cyber-crime has always been financially motivated, and banking Trojans or botnets have been some of the primary drivers of botnet traffic and malicious activities. 
 
For example, The GameOver ZeuS (GOZ) group, was a crime ring that focused on corporate banking account takeovers, with an estimated 100 million dollars of losses attributed to the group. 
 
The steps below describe in greater detail how APT-based banking Trojan typically works: 
 
1. Reconnaissance and Weaponisation: Gathering information and preparation of an attack. Using Carbanak APT [22] as an example, Cyber-criminals registered new spoofing domains to impersonate a legitimate software or tech company in later spear phishing emails claiming required software update. 
2. Delivery: Common methods of malicious payload delivery by banking Trojans are email attachments, social engineering and drive by download through spear phishing campaigns targeting employees within the victim organisations. 
3. Exploitation and Installation: If an employee within the targeted organizations opened the attachments or visited the malicious websites in above spear phishing emails, the vulnerability is successfully exploited, and backdoor is installed on the victim’s system. 
4. Command and Control: Command-and-control (C2) infrastructure plays an essential role in coordinating botnets and malware. Attackers set up C2 servers to distribute commands or harvest sensitive data from victims’ computers, or gain access to the critical systems in the victim’s infrastructure. Many sophisticated malware families contain domain generation algorithms (DGAs) to generate pseudo-random domains in bulk to evade public blacklists. 
5. Action on Objectives: Once the attackers successfully compromised the victim’s networks, especially the critical systems such as money processing services or financial accounts, attackers can now perform fraudulent transactions or cash out. 
 
JPMorgan Chase is integrating AI into its internal security systems to thwart malware infections within its own networks.
The banls Technology and IT experts the describe how deep learning can be used to identify malicious activity, such as spyware on staff PCs attempting to connect to hackers' servers on the public internet. It can also finger URLs in received emails as suspicious. And it’s not just an academic exercise: some of these AI-based programs are already in production use within the financial giant.
 
The aim is to detect and neutralize malware that an employee may have accidentally installed on their workstation after, say, opening a booby-trapped attachment in a spear-phishing email. It can also block web-browser links that would lead the employee to a page that would attempt to install malware on their computer.
 
Neural networks can be trained to act as classifiers, and predict whether connections to the outside world are legit or fake: bogus connections may well be, for example, attempts by snoop-ware on an infected PC to reach the outside world, or a link to a drive-by-download site. These decisions are thus based on the URL or domain name used to open the connection. 
Specifically, long-short term memory networks (LSTM) used in the bank's AI software can predict if a particular URL or domain name is real or fake. The engineers trained theirs using a mixture of private and public datasets.
 
The public datasets included a list of real domains scraped from the top million websites as listed by Alexa; they also used 30 different Domain Generation Algorithms (DGA), typically used by malware, to spin up a million fake malicious domains. For the URL data, they took 300,000 benign URLs from the DMOZ Open Directory Project dataset and 267,418 phishing URLS from the Phishtank dataset. The researchers didn’t specify the proportion of data used for training, validation, and testing.
 
You might think just firewalling off and logging all network traffic from bank workers' PCs to the outside world would do the trick in catching naughty connections and thus has turned to machine-learning to improve its network monitoring while allowing ongoing connections.
 
How it Works
First, the string of characters in a particular URL or domain name to be checked are converted into vectors and fed into the LSTM as input. The model then spits out a number or probability that the URL or domain name is bogus.
 
The LSTM was able to a performance of 0.9956 (with one being the optimal result) when classifying phishing URLs and 91 per cent accuracy for DGA domains, with a 0.7 per cent false positive rate. AI is well adapted to discovering the common patterns and techniques used in malicious software, and can even be more effective than traditional URL and domain-name filters.
 
“Advanced Artificial Intelligence (AI) techniques, such as Deep learning, Graph analysis, play a more significant role in reducing the time and cost of manual feature engineering and discovering unknown patterns for Cyber security analysts,” the bank's researchers told The Register.
 
Next, they hope to experiment with other types of neural networks like convolutional neural networks and recurrent neural networks to clamp down on the spread of malware even further. 
 
The Regsister:     Arvix
 
You Might Also Read:
 
Malware Attacks Drop As Encrypted Attacks Increase:
 
Five Hi -Tech Ways To Fight Off Cyber Attackers:
 
 
 
« US National Security Agency’s Cyber Offensive
Is The Cloud Skills Gap A Problem? »

CyberSecurity Jobsite
Perimeter 81

Directory of Suppliers

LockLizard

LockLizard

Locklizard provides PDF DRM software that protects PDF documents from unauthorized access and misuse. Share and sell documents securely - prevent document leakage, sharing and piracy.

NordLayer

NordLayer

NordLayer is an adaptive network access security solution for modern businesses — from the world’s most trusted cybersecurity brand, Nord Security. 

CSI Consulting Services

CSI Consulting Services

Get Advice From The Experts: * Training * Penetration Testing * Data Governance * GDPR Compliance. Connecting you to the best in the business.

ON-DEMAND WEBINAR: What Is A Next-Generation Firewall (and why does it matter)?

ON-DEMAND WEBINAR: What Is A Next-Generation Firewall (and why does it matter)?

Watch this webinar to hear security experts from Amazon Web Services (AWS) and SANS break down the myths and realities of what an NGFW is, how to use one, and what it can do for your security posture.

XYPRO Technology

XYPRO Technology

XYPRO is the market leader in HPE Non-Stop Security, Risk Management and Compliance.

Protective Intelligence

Protective Intelligence

Protective Intelligence brings together a group of information security specialists with a passion for delivering high-quality solutions.

European Defence Agency (EDA)

European Defence Agency (EDA)

EDAs mission is to improve European defence capabilities. Programme areas include Cyber Defence.

BruCON

BruCON

Brucon is Belgiums premium security and hacking conference.

CCN-CERT

CCN-CERT

CCN-CERT is the Spanish national government computer security incident response centre.

BigID

BigID

BigID is redefining personal data protection and privacy. BigID software helps companies secure their customer data & satisfy privacy regulations like GDPR.

Nexusguard

Nexusguard

Nexusguard is at the forefront of the fight against malicious Internet attacks, protecting organizations worldwide from threats to their websites, services, and reputations.

TEISS

TEISS

Teiss.co.uk is a website dedicated to providing information about cyber security. TEISS also provide a series of conferences and events focused on cyber security.

Cyber Tec Security

Cyber Tec Security

Cyber Tec Security is an IASME Certification Body for Cyber Essentials basic/Plus. We also provide ongoing Managed Security Services.

Kleiner Perkins

Kleiner Perkins

For five decades, Kleiner Perkins has made history by partnering with some of the most ingenious and forward-thinking founders in technology and life sciences.

Raonsecure

Raonsecure

Raonsecure is one of Korea’s leading ICT security software companies – providing a variety of PC and mobile security solutions to financial institutions, government, and enterprise.

AaDya

AaDya

AaDya provide smart, simple, affordable and effective cybersecurity software solutions for small and medium businesses.

Horizon3.ai

Horizon3.ai

Horizon3.ai is a leader in security assessment and validation enabling continuous security overwatch from an attacker’s perspective through our NodeZero SaaS solution.

ShieldApps

ShieldApps

ShieldApps comprehensive suite of products is designed to protect your personal devices from privacy threats, including hacking attempts, online tracking, fingerprinting, phishing, malware, and more.

Q5id

Q5id

At Q5id, we prove that your customers' digital identity and real-world identity are the same, our verification and authentication solution delivers a Proven and Secure digital identity for everyone.

Core to Cloud

Core to Cloud

Core to Cloud provide consultancy and technical support for the planning and implementation of sustainable security strategies.

Indevtech

Indevtech

Indevtech has been serving Hawaii since 2001, providing end-to-end managed IT services to small- and medium-businesses.