Juan is an experienced CTO with a demonstrated history of working in the computer and network security industry. He is an information technology professional skilled in SAP and Oracle applications, computer forensics, vulnerabilities research, IPS/IDS and information security.
Unless you’ve been on a retreat in some far-flung location with no internet access for the past few months, chances are you’re well aware of how much hype and fear there’s been around ChatGPT, the artificial intelligence (AI) chatbot developed by OpenAI. Maybe you’ve seen articles about academics and teachers worrying that it’ll make cheating easier than ever. On the other side of the coin, you might have seen the articles evangelising all of ChatGPT’s potential applications.
Alternatively, you may have been tickled by some of the more esoteric examples of people using the tool. One user, for example, got it to write an instruction guide for removing peanut butter sandwiches from a VCR in the style of the King James Bible. Another asked it to write a song in the style of Nick Cave; the singer was less than enthused about the results.
But amidst all that hype and discussion, there hasn’t been nearly enough attention paid to the risks and rewards that AI tools like ChatGPT present in the cybersecurity arena.
Understanding ChatGPT
In order to get a clearer idea of what those risks and rewards look like, it’s important to get a better understanding of what ChatGPT is and what it’s capable of.
ChatGPT (now in its latest version, ChatGPT-4, released on March 14th, 2023) is part of a larger family of AI tools developed by the US-based company OpenAI. While it’s officially called a chatbot, that doesn’t quite cover its versatility. Trained using both supervised and reinforcement learning techniques, it can do far more than most chatbots. As part of its responses, it can generate content based on all the information it was trained on. That information includes general knowledge as well as programming languages and code. As a result, it can, for instance, simulate an entire chat room; play games like tic-tac-toe; and simulate an ATM.
More importantly, for businesses and other large organisations, it can help improve businesses’ customer service through more personalised, accurate messaging. It can even write and debug computer programs. Some of those, and other, features mean that it could both be a cybersecurity ally and a threat.
Education, filtering, and bolstering defences
On the positive front, there’s a lot to be said for ChatGPT. One of the most valuable roles it could play is also one of the most simple: spotting phishing. Organisations could entrench a habit in their employees whereby they use ChatGPT to determine if any content they’re not sure about is phishing or if it was generated with malicious intent.
That’s important because, for all the technological advances made in recent years, social engineering attacks like phishing remain one of the most effective forms of cybercrime. In fact, research shows that, of the cyberattacks successfully identified in the UK in 2022, 83% involved some form of phishing.
Of course, there are numerous other ways that ChatGPT can be used to bolster cybersecurity efforts. It could, for example, provide a degree of assistance to more junior security workers, whether that’s in communicating any issues they might have or helping them better understand the context of what they’re meant to be working on at any given point. It could also help under-resourced teams curate the latest threats and in identifying internal vulnerabilities.
The bad guys are using it too
But even as cybersecurity professionals explore ways of using ChatGPT to their advantage, cybercriminals are too. They might, for example, make use of its ability to generate malicious code. Alternatively, they might use it to generate content that appears to be human-generated, potentially used to trick users into clicking on malicious links, unknowingly leading to dangerous consequences.
Some are even using ChatGPT to convincingly mimic legitimate AI assistants on corporate websites, opening up a new avenue in the social engineering battlefront. Remember, the success of cybercriminals largely depends on being able to target as many possible vulnerabilities, as frequently and quickly as possible. AI tools like ChatGPT allow them to do that by essentially acting as a supercharged assistant that can help create all assets needed for malicious campaigns.
Use the tools available
It should be clear then that, if cybercriminals are using ChatGPT and other AI tools to enhance their attacks, your security team should also be using them to bolster your cybersecurity efforts. Fortunately, you don’t have to do it alone.
The right security provider won’t just engage in constant research around how cybercriminals are using the latest technologies to enhance their attacks but also how those technologies can be used to improve threat detection, prevention, and defence. And with the damage that a cybersecurity attack can do to your critical infrastructure, it’s something they should be proactively telling you about too.
ChatGPT-4
With the latest release of ChatGPT (ChatGPT-4), OpenAI has made available the latest and most powerful conversational model, also introducing more controls to prevent its misuse. We asked ChatGPT “What could prevent malicious actors using ChatGPT with malicious intent” and this was the answer:
“There are several measures that could prevent malicious actors from using ChatGPT with malicious intent:
1. Access controls: OpenAl, the organization behind ChatGPT, has implemented access controls to limit who can access their API and use their technology. By restricting access, they can prevent malicious actors from using their technology for malicious purposes.
2. Monitoring and detection: OpenAl monitors the usage of their technology to detect and prevent malicious activities. They use machine learning models to identify patterns and anomalies in usage that could indicate potential misuse.
3. Ethical guidelines: OpenAl has published guidelines for responsible use of their technology, which outline best practices and ethical considerations. By following these guidelines, users can ensure that they are using the technology in a responsible and ethical manner.
4. User education: Education and awareness can help prevent the misuse of technology.
OpenAl provides resources and educational materials to help users understand the capabilities and limitations of their technology, as well as the potential risks of misuse.
5. Legal consequences: There are legal consequences for using technology like chatGPT for malicious purposes. Governments and law enforcement agencies have laws and regulations in place to punish individuals and organizations that use technology for illegal activities.
Overall, preventing malicious actors from using ChatGPT with malicious intent requires a combination of technical controls, ethical guidelines, user education, and legal consequences. It is important to use Al language models like ChatGPT responsibly and ethically to prevent the technology from being misused for harmful purposes.”
So ChatGPT went ahead and enumerated all of the measures that OpenAI has taken in order to prevent its misuse.
OpenAI, in the release blog of ChatGPT-4, explained how this model is supposedly safer than its predecessors: “We spent 6 months making GPT-4 safer and more aligned. GPT-4 is 82% less likely to respond to requests for disallowed content and 40% more likely to produce factual responses than GPT-3.5 on our internal evaluations”.
All this indicates that the right measures continue being improved to avoid its misuse, but as we all know the bad guys will continue to find ways to overcome those limitations as the model is more widely used and understood.
Want to learn more about AI and big data from industry leaders? Check out AI & Big Data Expo taking place in Amsterdam, California, and London. The event is co-located with Cyber Security & Cloud Expo.
Explore other upcoming enterprise technology events and webinars powered by TechForge here.
Related posts
Nigeria’s Former Jonathan Tells African Leaders To Put Humanity First
Joke Falaju, Abuja Bags African Heritage awardFormer President Goodluck Jonathan has urged African leaders privilege to hold public offices to become servants of the people, and not turn themselves into the “bosses of the people”.Jonathan stated this while receiving the African Democracy and Peace Icon…
7th Edition Connected Banking Summit East Africa – Innovation & Excellence Awards 2023 Concludes
POSTED ON MARCH 28, 2023 BY AFRICA BUSINESS The Summit brought together the best and brightest minds in the banking, financial services, fintechs and techfin sectors. The event, which took place on 7th March 2023, featured insightful speakers, award-winning companies, and top-notch sponsors. Attendees were treated to a range…
2020 Awards | Social Media For Social Good Award Announces 100 Micro & Macro Social Media Influencers For Good
Social Media For Social Good Award Announces 100 Micro & Macro Social Media Influencers For Good and Set To Award 25 Of Them On The 13th Of June 2020. The most anticipated list of Nigerians using social media for social good which is curated by…
Ergonomic Furniture Dealer Formfunc Studio Awarded SA’s First 6-Star Green Star Award
-African Independent The Green Building Council of South Africa (GBCSA) has awarded Cape Town-based Formfunc Studio, a leading ergonomic furniture supplier, a 6-star Green Star rating following the recent fit-out of their office, showroom and DC in Johannesburg. The project, led by specialist sustainability and…
The Risk And Reward Of ChatGPT In Cybersecurity
Juan is an experienced CTO with a demonstrated history of working in the computer and network security industry. He is an information technology professional skilled in SAP and Oracle applications, computer forensics, vulnerabilities research, IPS/IDS and information security. Unless you’ve been on a retreat in…
Explained – History Of Money From Fiat To Crypto
What is money? Money as a concept has been a cornerstone of human civilization and economic development. To start with the latter, money is a method of storing value and worth, and it also functions as a medium of exchange that allows individuals to exchange…
Studies Show That Nigerian Crypto Foreign Investment Is At A Record Low
Foreign direct investment in Nigeria fell by 33% last year due to a severe shortage of dollars, which discouraged crypto companies from expanding into the country. The largest economy in Africa has a foreign investment problem despite exponential growth in crypto adoption. The National Bureau…
Growing The Bitcoin Development Ecosystem In Africa
– Abubakar Nur Khalil | Bitcoin Magazine Bitcoin development in Africa, with a proper regulatory environment, could equally accelerate the continent and the technology. In this piece, we’ll be analyzing the current state of the Bitcoin developer ecosystem in Africa, ways to improve it and…