While creating a bioweapon may be cheaper than defending against it, biology is inherently defense-dominant. Pathogens are vulnerable to physical barriers, filtration, heat, and UV light. Their small size is a weakness, and unlike intelligent adversaries, they cannot strategically penetrate defenses, giving defenders a fundamental advantage.
Related Insights
Models designed to predict and screen out compounds toxic to human cells have a serious dual-use problem. A malicious actor could repurpose the exact same technology to search for or design novel, highly toxic molecules for which no countermeasures exist, a risk the researchers initially overlooked.
Defenders of AI models are "fighting against infinity" because as model capabilities and complexity grow, the potential attack surface area expands faster than it can be secured. This gives attackers a persistent upper hand in the cat-and-mouse game of AI security.
In defense technology, smaller is often better. The ideal platform is the most compact one that can still perform its intended mission. This approach provides significant advantages in stealth, manufacturing cost, logistical footprint, and speed of proliferation.
Unlike a drug that can be synthesized to a chemical standard, most vaccines are living biological products. This means the entire manufacturing process must be perfectly managed and cannot be altered without re-validation. This biological complexity makes production far more difficult and expensive than typical pharmaceuticals.
The danger of AI creating harmful proteins is not in the digital design but in its physical creation. A protein sequence on a computer is harmless. The critical control point is the gene synthesis process. Therefore, biosecurity efforts should focus on providing advanced screening tools to synthesis providers.
With directed evolution, scientists find a mutated enzyme that works without knowing why. Even with the "answer"—the exact genetic changes—the complexity of protein interactions makes it incredibly difficult to reverse-engineer the underlying mechanism. The solution often precedes the understanding.
Current biosecurity screens for threats by matching DNA sequences to known pathogens. However, AI can design novel proteins that perform a harmful function without any sequence similarity to existing threats. This necessitates new security tools that can predict a protein's function, a concept termed "defensive acceleration."
The AI-discovered antibiotic Halicin showed no evolved resistance in E. coli after 30 days. This is likely because it hits multiple protein targets simultaneously, a complex property that AI is well-suited to identify and which makes it exponentially harder for bacteria to develop resistance.
Most AI "defense in depth" systems fail because their layers are correlated, often using the same base model. A successful approach requires creating genuinely independent defensive components. Even if each layer is individually weak, their independence makes it combinatorially harder for an attacker to bypass them all.
Valthos CEO Kathleen, a biodefense expert, warns that AI's primary threat in biology is asymmetry. It drastically reduces the cost and expertise required to engineer a pathogen. The primary concern is no longer just sophisticated state-sponsored programs but small groups of graduate students with lab access, massively expanding the threat landscape.
