Criminals Are Becoming More Efficient With AI
Criminals are now using AI to improve document forgery and exploit security gaps, increasing the scale and sophistication of their attacks. AI's rapid development challenges security experts and demands new strategies to handle these threats.
AI is also being used to write malware and exploit vulnerabilities in various systems. A study from the University of Illinois Urbana-Champaign (UIUC) showed that researchers used OpenAI's GPT-4 to autonomously exploit vulnerabilities in real-world systems by feeding the model CVE advisories. The study found that GPT-4 could exploit 87% of the tested vulnerabilities, a clear improvement over previous versions of the AI model. This capability could allow cybercriminals to exploit new vulnerabilities quickly and efficiently, posing a serious security risk.
AI and National Security Threats
National security agencies around the world are aware of the potential risks of AI in the hands of criminals and state-sponsored actors. Microsoft and OpenAI have identified several state-funded groups using AI to improve their cyber operations. These include groups from Russia, North Korea, Iran, and China, which use AI for everything from vulnerability analysis to crafting phishing emails and gathering information about specific organizations.
Rapid Adaptation and New Risks
The rapid growth of AI has led to both major advances and unintended consequences. For example, AI-powered search engines have recommended scam sites, and security researchers have discovered vulnerabilities in several AI applications. In addition, legal issues have arisen around content used to train large language models (LLMs), with claims of copyright infringement from authors and media organizations.
The growing use of AI by cybercriminals poses a significant challenge for security experts and lawmakers. While AI technology can offer substantial productivity gains and efficiency, these benefits are now being exploited by criminals to increase the scale and sophistication of their attacks. Future strategies must include addressing the unique threats AI poses, while maximizing the technology's positive potential for business and society.