Looking ahead to the AI Seoul Summit

How summits in Seoul, France and past can impress worldwide cooperation on frontier AI security

Final yr, the UK Authorities hosted the primary main world Summit on frontier AI security at Bletchley Park. It centered the world’s consideration on fast progress on the frontier of AI growth and delivered concrete worldwide motion to reply to potential future dangers, together with the Bletchley Declaration; new AI Security Institutes; and the International Scientific Report on Advanced AI Safety.

Six months on from Bletchley, the worldwide group has a chance to construct on that momentum and impress additional world cooperation at this week’s AI Seoul Summit. We share under some ideas on how the summit – and future ones – can drive progress in direction of a standard, world strategy to frontier AI security.

AI capabilities have continued to advance at a fast tempo

Since Bletchley, there was sturdy innovation and progress throughout your entire area, together with from Google DeepMind. AI continues to drive breakthroughs in essential scientific domains, with our new AlphaFold 3 mannequin predicting the construction and interactions of all life’s molecules with unprecedented accuracy. This work will assist rework our understanding of the organic world and speed up drug discovery. On the identical time, our Gemini family of models have already made merchandise utilized by billions of individuals all over the world extra helpful and accessible. We have additionally been working to enhance how our fashions understand, motive and work together and just lately shared our progress in constructing the way forward for AI assistants with Project Astra.

This progress on AI capabilities guarantees to enhance many individuals’s lives, but additionally raises novel questions that have to be tackled collaboratively in various key security domains. Google DeepMind is working to establish and tackle these challenges by pioneering security analysis. Up to now few months alone, we’ve shared our evolving approach to creating a holistic set of security and duty evaluations for our superior fashions, together with early research evaluating essential capabilities similar to deception, cyber-security, self-proliferation, and self-reasoning. We additionally launched an in-depth exploration into aligning future advanced AI assistants with human values and pursuits. Past LLMs, we just lately shared our strategy to biosecurity for AlphaFold 3.

This work is pushed by our conviction that we have to innovate on security and governance as quick as we innovate on capabilities – and that each issues should be carried out in tandem, constantly informing and strengthening one another.

Constructing worldwide consensus on frontier AI dangers

Maximizing the advantages from superior AI methods requires constructing worldwide consensus on essential frontier issues of safety, together with anticipating and getting ready for brand new dangers past these posed by current day fashions. Nevertheless, given the excessive diploma of uncertainty about these potential future dangers, there may be clear demand from policymakers for an unbiased, scientifically-grounded view.

That’s why the launch of the brand new interim International Scientific Report on the Safety of Advanced AI is a crucial element of the AI Seoul Summit – and we sit up for submitting proof from our analysis later this yr. Over time, such a effort may develop into a central enter to the summit course of and, if profitable, we consider it needs to be given a extra everlasting standing, loosely modeled on the operate of the Intergovernmental Panel on Local weather Change. This could be an important contribution to the proof base that policymakers all over the world want to tell worldwide motion.

We consider these AI summits can present a daily discussion board devoted to constructing worldwide consensus and a standard, coordinated strategy to governance. Preserving a singular give attention to frontier security may even guarantee these convenings are complementary and never duplicative of different worldwide governance efforts.

Establishing greatest practices in evaluations and a coherent governance framework

Evaluations are a essential element wanted to tell AI governance selections. They allow us to measure the capabilities, habits and impression of an AI system, and are an essential enter for threat assessments and designing applicable mitigations. Nevertheless, the science of frontier AI security evaluations remains to be early in its growth.

That is why the Frontier Model Forum (FMF), which Google launched with different main AI labs, is participating with AI Security Institutes within the US and UK and different stakeholders on greatest practices for evaluating frontier fashions. The AI summits may assist scale this work internationally and assist keep away from a patchwork of nationwide testing and governance regimes which can be duplicative or in battle with each other. It’s essential that we keep away from fragmentation that would inadvertently hurt security or innovation.

The US and UK AI Security Institutes have already agreed to construct a standard strategy to security testing, an essential first step towards higher coordination. We expect there is a chance over time to construct on this in direction of a standard, world strategy. An preliminary precedence from the Seoul Summit could possibly be to agree a roadmap for a variety of actors to collaborate on creating and standardizing frontier AI analysis benchmarks and approaches.

It would even be essential to develop shared frameworks for threat administration. To contribute to those discussions, we just lately launched the primary model of our Frontier Safety Framework, a set of protocols for proactively figuring out future AI capabilities that would trigger extreme hurt and putting in mechanisms to detect and mitigate them. We anticipate the Framework to evolve considerably as we be taught from its implementation, deepen our understanding of AI dangers and evaluations, and collaborate with business, academia and authorities. Over time, we hope that sharing our approaches will facilitate work with others to agree on requirements and greatest practices for evaluating the security of future generations of AI fashions.

In direction of a worldwide strategy for frontier AI security

Lots of the potential dangers that would come up from progress on the frontier of AI are world in nature. As we head into the AI Seoul Summit, and sit up for future summits in France and past, we’re excited for the chance to advance world cooperation on frontier AI security. It’s our hope that these summits will present a devoted discussion board for progress in direction of a standard, world strategy. Getting this proper is a essential step in direction of unlocking the large advantages of AI for society.