Jam Kraprayoon

The UK @AISecurityInst has proven AI agents can orchestrate cyberattacks. To defend against these emerging threats, we must detect them. New research from @iapsAI and @aisafetysg shows why detecting offensive cyber agents will be difficult — and what we should do about it.

“The United States and its allies have years, not decades, before autonomous cyber-capabilities proliferate,” write @rosen_br and @JKraprayoon. What should Washington do now to mitigate potential security risks? foreignaffairs.com/united-states/…

While initiatives like Project Glasswing provide tech companies with access to cyber-capable models, "access is only the starting point". A timely policy memo on AI cyber defence, by @covinstantinop, @JKraprayoon, & @MattInThemittel @iapsAI

Mythos is a leap in AI cyber capabilities, but the bigger story is the accelerating trajectory and proliferation. @iapsAI researcher Christopher Covino explores what the preview means for national security and what policymakers should do about it: iaps.ai/research/mytho…

“Autonomous cyber-agents are already operational, and policymakers are unprepared.” Read @rosen_br and @JKraprayoon on the threat that AI agents pose to global security—and how governments should respond: foreignaffairs.com/united-states/…

.@rosen_br and @JKraprayoon examine the security risks posed by autonomous cyber-agents—and urge Washington to shore up its defenses “before AI goes rogue.” foreignaffairs.com/united-states/…

“The policy choices made today will determine whether autonomous cyber-agents become a manageable risk or an uncontrollable one,” write @rosen_br and @JKraprayoon. fam.ag/4dLV66m

Autonomous cyber-agents can already execute in minutes what would take hours of expert human labor — with no off switch and no capacity to judge when to stop. Today in @ForeignAffairs, IAPS's @rosen_br and @JKraprayoon discuss what this means for national security: foreignaffairs.com/united-states/…

New post on Substack: Securing AI Infrastructure to Prevent Backdoors and Sabotage In an intense AI race, we may expect adversaries (nation-states, insiders, maybe even misaligned AIs) to target our frontier AI models through data poisoning and other integrity attacks One of the best ways to stop these kinds of attacks is securing our AI infra My new post explores open problems in securing AI infrastructure and outlines a concrete research agenda the-substrate.net/p/securing-ai-…

3/3 It distills key findings from our recent @iapsAI report on Highly Autonomous Cyber-Capable Agents (HACCAs) — systems that can independently conduct end-to-end cyber campaigns at the level top criminal groups and nation-state hackers iaps.ai/research/highl…

2/3 @shaunkeee and I have an op-ed out in Just Security: "When AI Runs the Operations: Autonomous Agents and the Future of Cyber Competition." justsecurity.org/133668/ai-agen…

1/3 The White House's new Cyber Strategy commits to "rapidly adopt and promote agentic AI in ways that securely scale network defense and disruption." But what happens when adversaries deploy the same capabilities — and what if we lose control of our own? 🧵

11/ We hope researchers, security practitioners, and policymakers will build on this. We'd genuinely welcome pushback, extensions, and collaboration. Thanks to my co-authors: @shaunkeee, @rosen_br, Chris Covino, Aditya Singh, Yohan Matthew, and Asher Brass

10/ Some hard questions we think the field needs to tackle: How do you defend organizations that can barely handle today's threats against autonomous attackers? How do you govern systems literally designed to overcome safeguards?

1/ A few months ago, my co-authors and I at @iapsAI set out to answer a question that felt increasingly urgent: what happens when AI systems can run sophisticated cyber operations entirely on their own?