There is a 163% increase in crypto-jacking for browser-searches in 2020 than the previous quarter in 2019, according to US Cybersecurity firm Symantec in its recent findings.

With the hype of news we have heard lately, such as the hijacking of Youtube and other social media accounts and the regular accounts of celebrities and big wigs, this could be well-proven.
“After a sharp decline in cryptojacking following the shutdown of browser-based mining script maker CoinHive in March 2019, the second quarter of 2020 saw resurgence inactivity,” said Symantec in the report confirming that the jolt coincided “with an increase in the value of cryptocurrencies, including Bitcoin and Monero which are two currencies often mined by browser-based coin miners.”
According to the number, the record level is exploding as early as June, hitting 48,697. This figure has shattered the pattern observed since the early this 2020 when cryptojacking incidents are seen to fall from 8,407 attacks in January to 5,403 incidents in May.
To solve this emerging problem, some scientists are crafting solutions based on artificial intelligence aiming to halt criminals from hijacking primarily through its victim’s devices.
On the other hand, research on AI has been developing. This includes figuring how the learning system can detect abusive codes by being keen on their similarities. This adds hope that even more efficient tools against cryptojacking are also lined up in the future.
Cryptojacking rose to fame as the term for unauthorized use of someone’s computer to mine cryptocurrency, usually gaining access by tricking the victim into clicking on a malicious link, through an infected website, etc.
A team of researchers from Los Alamos National Laboratory and New York University, who published in the IEEE Access journal a paper called “Code Characterization Wih Code Characterization With Graph Convolutions and Capsule Networks, narrated the use of an AI-based system to identify illicit crypto mining by observing comparisons its code to its legitimate counterpart.
Also, the researchers posit that, as all programs can be signified by graphs that comprise nodes linked by lines, loops, or jumps, their AI system could be used to compare “the contours in a program’s flow-control graph to a catalog of graphs for programs that are allowed to run on a given computer.”
“Our deep learning artificial intelligence model is designed to detect the abusive use of supercomputers specifically for the purpose of cryptocurrency mining,” quoted Gopinath Chennupati, a researcher at LANL and co-author of the paper.
He also detailed that “based on recent computer break-ins in Europe and elsewhere, this type of software watchdog will soon be crucial to prevent cryptocurrency miners from hacking into high-performance computing facilities and stealing precious computing resources.”
No Comment