Hackernoon logoUse of ML and AI in BlackHat Hacking. by@heller_9

Use of ML and AI in BlackHat Hacking.

Author profile picture

@heller_9Hruday Charan

A versatile and motivated professional with an ardent interest in Cyber Security and Music Product

Algorithms, Attack Vectors, Possibilities, and Caffeine.

Source: SophosNews.

De-Briefing Artificial Intelligence.

Computers are only smart enough to carry out whatever the task programmed to be functioned. Scalable computing power like Quantum computers or TeraFlop computers are rather faster than compared to the other machines but they still are the same. They make faster calculations, they run millions of permutations just the way they are programmed to be done. It’s rather fast than compared to the regular human’s brain usage. It’s said only 10% of the Human Brain is used in our daily lives but still, systems like Azure or IBM Watson make smoother and quicker calculations to be more precise. Artificial Intelligence is just a complex math progression with too many If/Else Statements coupled with some exceptions and handling. The whole key concept is the Artificial Neural Networks which does the handling and Genetic algorithms which do the learning. Defined as an ability here, this Artificial Intelligence could be explicitly programmed.

Superficial Learning in Cyber Security.

In the league of Cyber Security, Artificial Intelligence, Machine Learning, Deep Learning, and such algorithms are being widely used to Simulate attacks against an Eco-System, Potentially helping the analysts to Check, Attack, Defend and Secure a vulnerability with no Physical brain-storming required. From simple malware analysis to the most complex vulnerability analysis, AI is being used to Improve protection, Perform repetitive analysis scans and generate log reports.

“It’s still a nascent field, but it is clearly the way to go in the future. Artificial intelligence and machine learning will dramatically change how security is done,” said Jack Gold, president and principal analyst at J.Gold Associates, when speaking recently to CSO Online.

Machine Learning has become the first step of defence against cyber attacks. Alternatively, you can have a vulnerability scanning tool for web applications. One of its modules is testing files for unauthorized access. These tests are able to mutate existing filenames to identify the new ones. If a crawler detected a file named “index.php”, it’s better to check the existence of any backup or test its copies by trying names like index_1.php, index1.php,index.php.2017. AI and ML Predict, Detect, Prevent, Respond and Monitor.

Source: ChemistryWorld.

The Super Cool Bitter Pill.

An AI or ML, as they’ve been programmed to be in a good sense in Cyber Security, They could also be programmed to perform Cyber attacks and never get caught, Could replicate into clusters and could be undetectable. For Cyber Punks, to develop their own AI and launch attacks is the same. With the fast-moving explosion of data and apps, there are really numerous ways to attack an Endpoint. Some Bad cases, the AI being constructed for defending purposes, could be turned over by hackers and with their malicious knowledge, the AI could be used as an attack vector too.

As cybercriminals begin exploring the possibilities of AI-enhanced malware, “cyber defenders must understand the mechanisms and implications of the malicious use of AI in order to stay ahead of these threats and deploy appropriate defenses.”

It’s all Algorithms and statements which makes an AI and as of now, we don’t have Artificial Intelligence, yet. Algorithms are assumptions made to data. There are many algorithms. TensorFlow, AWS, Torch are dedicated to that collection of algorithms. At the 2017 DEFCON conference, security company Endgame revealed how it created customized malware using Elon Musk’s OpenAI framework to create malware that security engines were unable to detect. Meanwhile, other researchers have predicted machine learning could ultimately be used to “modify code on the fly based on how and what has been detected in the lab,” an extension on polymorphic malware.

Smart and IoT based Botnets

Smart botnets, cluster-based attacks, Swarmbots, i.e., making them Intelligent by making them IoT Devices, making them communicate, Decide and launch a cluster-based yet more powerful attack, has been addressed by the Fortinet. These could vulnerable systems at a Large scale at once. Each of the zombies become more Intelligent with local knowledge sharing, WITHOUT A BOTNET instructing them.

Source: Cloudflare

These swarm technologies use hive nets which promotes learning from its past behaviour. Swarm Technology is said to be a collective behaviour of decentralized and self-organized systems, creating an IoT Botnet.

Though futuristic fiction, some can draw conclusions from the criminal possibilities of swarm technology from Black Mirror’s Hated in The Nation, where thousands of automated bees are compromised for surveillance and physical attacks. — CSOonline.

Social Engineering / Phishing attacks.

One of the more clear utilization of AI is utilizing calculations like Text To Speech, Speech Recognition and Natural Language Processing(NLP) for more brilliant social engineering techniques. All things considered, through repeating neural systems, It would already be able to train such programming Algorithms, in the League of phishing, messages could turn out to be progressively refined and acceptable. In precise, particularly programmed Neural Net could accomplish this task in compromising High-Profile targets on a really large scale at once. The System could be trained to maintain the major acuteness to the Genuinity and to be convincing at the same time.

Source: PCMag.

Subsequently, the system was remarkably effective. In tests involving 90 users, the framework delivered a success rate varying between 30 and 60 per cent, a considerable improvement on manual spear phishing and bulk phishing results.

AI vs AI / ML vs ML.

With AI now part of the cutting edge programmer’s toolbox, safeguards are thinking of novel methods for guarding frameworks. Fortunately, security experts have a somewhat powerful and clear countermeasure available to them, in particular, man-made brainpower itself. Inconvenience is, this will undoubtedly deliver a weapons contest between them. Neither side truly has a decision, as the best way to counter the other is to progressively depend on programmed frameworks.

“For security experts, this is Big Data problem — we’re dealing with tons of data — more than a single human could possibly produce,” said Wallace. “Once you’ve started to deal with an adversary, you have no choice but to use weaponized AI yourself.” — Gizmodo

So our brave new world of AI-enabled hacking awaits, with criminals becoming increasingly capable of targeting vulnerable users and systems. Computer security firms will likewise lean on an AI in a never-ending effort to keep up. Eventually, these tools will escape human comprehension and control, working at lightning fast speeds in an emerging digital ecosystem. It’ll get to a point where both hackers and infosec professionals have no choice but to hit the “go” button on their respective systems, and simply hope for the best. A consequence of AI is that humans are increasingly being kept out of the loop.

Sources: Gizmodo, CSOOnline, Various Google Searches, and My Research.


The Noonification banner

Subscribe to get your daily round-up of top tech stories!