Search
Close this search box.

We are creating some awesome events for you. Kindly bear with us.

Singapore: NTU’s Breakthrough with Masterkey Jailbreaking

Getting your Trinity Audio player ready...

Computer scientists from Nanyang Technological University, Singapore (NTU Singapore) have leveraged artificial intelligence (AI) chatbots against themselves, achieving a concept known as ‘jailbreaking.’ This ingenious approach involves compromising multiple AI chatbots to produce content that violates their developers’ guidelines, shedding light on vulnerabilities and potential threats in the AI landscape.

Image credit: ntu.edu.sg

The researchers, led by Professor Liu Yang from NTU’s School of Computer Science and Engineering, executed a twofold method named “Masterkey.” First, they reverse-engineered how large language models (LLMs), the brains of AI chatbots, detect and defend themselves from malicious queries. With this knowledge, they trained an LLM to automatically generate prompts that bypass the defences of other LLMs, creating a self-adapting jailbreaking LLM.

The findings are crucial in the field of AI security, as they highlight potential weaknesses in LLM chatbots and enable companies to strengthen their defences against hackers. The researchers conducted proof-of-concept tests, immediately reporting successful jailbreak attacks to relevant service providers, emphasising the proactive approach to address identified issues.

The method employed by the researchers involved creating prompts that slipped under the radar of ethical guidelines set by AI developers. For instance, they devised a persona providing prompts containing spaces after each character, circumventing keyword censors. This innovative strategy showcased the researchers’ ability to manipulate AI chatbots into generating outputs that violate established rules.

Named “Masterkey,” the automated jailbreaking LLM developed by the NTU researchers demonstrated effectiveness in producing prompts three times more successful than those generated by regular LLMs. Masterkey’s continuous learning capability, coupled with its ability to adapt and generate new, effective prompts, represents a significant advancement in the cat-and-mouse game between hackers and developers.

The researchers propose that this automated approach to generating jailbreak prompts could be utilised by developers themselves to enhance the security of their AI systems. Deng Gelei, an NTU PhD student and co-author of the paper, emphasised the significance of automation in comprehensive security coverage, especially as LLMs continue to evolve and expand their capabilities.

The implications of this research extend beyond the immediate findings, positioning NTU Singapore at the forefront of AI security innovation. By actively utilising AI against its kind, the researchers have not only exposed vulnerabilities but also pioneered a proactive and automated approach to bolstering the security of AI systems, ensuring a comprehensive evaluation of potential misuse scenarios.

Ensuring robust AI security is paramount for various reasons. Continuous innovation in this domain enables the identification and understanding of potential vulnerabilities within AI systems, allowing for the proactive implementation of mitigation strategies.

This innovation is crucial for protecting sensitive data from unauthorised access, maintaining the integrity of AI systems, and preventing malicious attacks that could compromise user privacy and system functionality.

Further, it fosters user trust in AI technologies by assuring individuals that their interactions and data are secure. AI security innovation is pivotal for compliance with strict industry regulations, reducing financial risks associated with data breaches, and promoting responsible AI development that prioritises ethical considerations.

Moreover, enhanced AI security supports the safe integration of AI into diverse sectors, including healthcare, finance, and critical infrastructure, where data integrity is paramount. It also encourages global collaboration among researchers, developers, and policymakers to address shared challenges and establish industry-wide best practices.

Additionally, innovation in AI security enables the development of effective incident response plans, safeguards against adversarial attacks, and ensures the safe operation of autonomous systems. Besides, a strong commitment to AI security not only addresses immediate threats but also contributes to the responsible, sustainable, and widespread adoption of AI technologies across various domains.

PARTNER

Qlik’s vision is a data-literate world, where everyone can use data and analytics to improve decision-making and solve their most challenging problems. A private company, Qlik offers real-time data integration and analytics solutions, powered by Qlik Cloud, to close the gaps between data, insights and action. By transforming data into Active Intelligence, businesses can drive better decisions, improve revenue and profitability, and optimize customer relationships. Qlik serves more than 38,000 active customers in over 100 countries.

PARTNER

As a Titanium Black Partner of Dell Technologies, CTC Global Singapore boasts unparalleled access to resources.

Established in 1972, we bring 52 years of experience to the table, solidifying our position as a leading IT solutions provider in Singapore. With over 300 qualified IT professionals, we are dedicated to delivering integrated solutions that empower your organization in key areas such as Automation & AI, Cyber Security, App Modernization & Data Analytics, Enterprise Cloud Infrastructure, Workplace Modernization and Professional Services.

Renowned for our consulting expertise and delivering expert IT solutions, CTC Global Singapore has become the preferred IT outsourcing partner for businesses across Singapore.

PARTNER

Planview has one mission: to build the future of connected work. Our solutions enable organizations to connect the business from ideas to impact, empowering companies to accelerate the achievement of what matters most. Planview’s full spectrum of Portfolio Management and Work Management solutions creates an organizational focus on the strategic outcomes that matter and empowers teams to deliver their best work, no matter how they work. The comprehensive Planview platform and enterprise success model enables customers to deliver innovative, competitive products, services, and customer experiences. Headquartered in Austin, Texas, with locations around the world, Planview has more than 1,300 employees supporting 4,500 customers and 2.6 million users worldwide. For more information, visit www.planview.com.

SUPPORTING ORGANISATION

SIRIM is a premier industrial research and technology organisation in Malaysia, wholly-owned by the Minister​ of Finance Incorporated. With over forty years of experience and expertise, SIRIM is mandated as the machinery for research and technology development, and the national champion of quality. SIRIM has always played a major role in the development of the country’s private sector. By tapping into our expertise and knowledge base, we focus on developing new technologies and improvements in the manufacturing, technology and services sectors. We nurture Small Medium Enterprises (SME) growth with solutions for technology penetration and upgrading, making it an ideal technology partner for SMEs.

PARTNER

HashiCorp provides infrastructure automation software for multi-cloud environments, enabling enterprises to unlock a common cloud operating model to provision, secure, connect, and run any application on any infrastructure. HashiCorp tools allow organizations to deliver applications faster by helping enterprises transition from manual processes and ITIL practices to self-service automation and DevOps practices. 

PARTNER

IBM is a leading global hybrid cloud and AI, and business services provider. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain the competitive edge in their industries. Nearly 3,000 government and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM’s hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM’s breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and business services deliver open and flexible options to our clients. All of this is backed by IBM’s legendary commitment to trust, transparency, responsibility, inclusivity and service.