Two Programmes, One Problem

AIThursday, October 22, 2026·9 min read

What DARPA's CLARA and SABER Programmes Reveal About Governing Autonomous AI at the Edge

Prove It, Then Break It

What DARPA's CLARA and SABER Programmes Reveal About Governing Autonomous AI at the Edge

Reference: EA/DEF/2026/002 · Date: 22 October 2026 · Series: Defence Technology & AI Governance

• • •

Two Programmes, One Problem

In 2025 and 2026, the US Defense Advanced Research Projects Agency (DARPA) launched two AI programmes that, read together, describe the central problem of autonomous systems more clearly than most policy documents do.

The first, CLARA, asks how to build AI whose behaviour can be proven. The second, SABER, asks how AI that is already fielded can be broken. One programme works on assurance from the inside, through mathematics and logic. The other works on assurance from the outside, through adversarial testing on a representative battlefield.

Neither alone is sufficient. A proof only holds over the model of the world it was written for, and an attacker's job is to find the places where the world departs from that model. A red team, in turn, can only demonstrate that it failed to break a system; it cannot demonstrate that the system cannot be broken. Governance of autonomous AI lives in the gap between the two.

• • •

CLARA: Building AI That Can Be Proven

ItemDetail
Full nameCompositional Learning-And-Reasoning for AI Complex Systems Engineering
OfficeDefense Sciences Office (DSO)
Programme managerBenjamin Grosof
FundingUp to US$2 million per project, as Other Transaction prototype agreements
Structure15-month Phase 1 base; 9-month Phase 2 option
Proposal deadline17 April 2026
Technical Area 1New high-assurance ML/AR theory, algorithms, and open-source software for inference and training
Technical Area 2A software integration library: common data formats, interfaces, end-to-end explainability tools

The core idea

Most current approaches to trustworthy AI bolt a reasoning component onto a large language model as a safeguard. DARPA's own description is pointed: the common practice is to "tack specialized automated reasoning (AR) components onto a large language model."

CLARA proposes the opposite. Machine learning (ML) and automated reasoning are composed together from the start, in a "hierarchical, fine-grained, highly transparent" structure. Bayesian models, neural networks and logic programs become interchangeable building blocks, and the target is "verifiability based on AR proofs that have strong logical explainability and computational tractability."

The listed application areas are revealing: kill webs, logistics, wargaming, autonomous and command-and-control systems, but also medical, financial and legal domains. CLARA is not a weapons programme. It is a bet that high-assurance AI is a general engineering discipline, in the same way that structural analysis is general.

NOTE: The phrase "computational tractability" matters for edge systems. A proof that takes hours to check cannot govern a vehicle that must decide in milliseconds. CLARA's insistence on tractable reasoning is, in effect, a real-time requirement.

• • •

SABER: Breaking AI Before the Adversary Does

ItemDetail
Full nameSecuring Artificial Intelligence for Battlefield Effective Robustness
Programme managerNathaniel Bastian
Target systemsAI-enabled autonomous ground and aerial systems that could be fielded within one to three years
Proposers Day12 March 2025
Threat classesData poisoning, physically constrained adversarial patches, model stealing
Techniques in scopePhysical, adversarial-AI, cybersecurity and electronic warfare methods

Known awards

PerformerValueReported role
BAE Systems Electronic SystemsUS$3.9 million (early February 2026)Counter-AI techniques and tools for operational assessment
Lockheed Martin Advanced Technology LaboratoriesUS$4.7 million (announced February 2026)Counter-AI techniques and tools for operational assessment
Kitware, with Scientific Systems CompanyUS$4 million, two years (May 2026)Physical-world adversarial attacks, evaluation tools, field testing on ground and rotary-wing systems

The core idea

SABER's starting observation is that adversarial attacks on AI have mostly been demonstrated in simulation or in physical settings with "relatively pristine control." Almost nobody has shown what happens when a poisoned dataset, a printed adversarial patch or a stolen model meets a real autonomous vehicle in a contested environment. DARPA's stated position is that no current methods exist to assess deployed military AI systems for these vulnerabilities.

The programme's deliverable is therefore not a single tool, but a repeatable model for operational AI red teaming: people, methods and test procedures that can be applied to each new system before it is trusted.

RISK: Every one of SABER's threat classes applies equally to civilian autonomy. A delivery drone, an agricultural UAV or a geospatial survey platform running onboard vision models is exposed to the same poisoning, patch and model-extraction attacks. The only difference is that nobody is funding a red team for them.

• • •

Why the Edge Changes Everything

Governing AI in a data centre is a policy problem. Governing AI at the edge is a control problem. Four conditions make it so:

No reliable link: An edge system may lose contact with its operators, exactly as a hypersonic vehicle loses GNSS in its plasma sheath. Governance that depends on a remote human approving each decision fails at the moment it is needed.

Tight resource limits: Size, weight, power and cost constraints rule out running large verification engines onboard. Any runtime check must be cheap.

Adversarial inputs: The sensors are pointed at the world, and the world can be edited. A patch on a vehicle or a pattern on a road is an attack on the perception stack that requires no network access at all.

Physical consequences: A wrong output is not a bad answer on a screen. It is a vehicle in the wrong place.

These conditions explain why the two programmes fit together. CLARA addresses what can be guaranteed onboard with limited compute. SABER addresses what the adversary will do to the inputs those guarantees depend on.

• • •

The AMANAH Lens: An Islamic Governance Ontology for Autonomy

The AMANAH framework approaches the same problem from a different direction. It draws on three concepts from the Islamic governance tradition and gives each an engineering interpretation.

Amanah: bounded, entrusted authority

Amanah is a trust held on behalf of another. The one who holds it is accountable for it and may not exceed it. For an autonomous system, this becomes a formal operating envelope: a set of states and actions within which the system is authorised to act alone, and outside of which it must defer, degrade or stop. Authority is delegated, never owned.

Muraqabah: continuous self-observation

Muraqabah is watchfulness, the awareness of being observed and the discipline of observing oneself. In engineering terms, this is a runtime monitor that runs continuously alongside the decision-making component and checks whether the system is still inside its envelope, and whether its inputs still look like the world it was trained on.

Adab: norms of conduct

Adab is right conduct: the rules of behaviour that hold regardless of the immediate goal. In engineering terms, these are explicit, inspectable constraints, which is precisely the role CLARA assigns to automated reasoning components composed alongside learned ones.

Mapping the frameworks

AMANAH principleEngineering mechanismCLARA contributionSABER contribution
Amanah (bounded authority)Safety envelope defined by a Lyapunov-type function; authority limited to the region where it is guaranteed to decreaseProofs that the composed system stays within the envelopeTests of whether adversaries can push the system across the boundary
Muraqabah (self-observation)Runtime assurance monitor; input-distribution checksTractable reasoning that can run in real timeEvidence of which attacks evade the monitor
Adab (norms of conduct)Explicit logical constraints composed with learned componentsHierarchical ML/AR composition with explainabilityValidation that constraints hold under poisoned or manipulated inputs

A concrete architecture

The mapping above corresponds to a well-established pattern in safety-critical control, often called the Simplex or runtime-assurance architecture:

An advanced controller (which may be a learned policy) handles normal operation and delivers high performance.

A verified safety controller, simple enough to be proven correct, can always return the system to a safe state.

A decision module monitors the state and hands control to the safety controller whenever the system approaches the edge of its envelope.

In AMANAH terms, the advanced controller exercises entrusted authority, the decision module performs muraqabah, and the safety controller embodies adab: the conduct that holds when everything else is uncertain. The Lyapunov function defines where the trust ends.

WARNING: Runtime assurance only works if the monitor's view of the state is honest. If an adversary can corrupt the sensor inputs, the monitor can be convinced that the system is safe when it is not. This is exactly the failure mode SABER is designed to expose, and it is why proof and red-teaming cannot be separated.

• • •

What This Means for Researchers Outside the United States

CLARA and SABER are US defence programmes, but their outputs and their lessons travel:

Open-source software is coming. CLARA's Technical Area 1 explicitly includes open-source software for inference and training. Research groups anywhere will be able to build on, benchmark against and critique it.

The red-team method is the transferable asset. SABER's lasting contribution is likely to be a methodology, not a weapon. A university UAV group can adopt the same discipline today: define the threat classes, attack your own perception stack physically, and publish what breaks.

Governance frameworks need engineering hooks. Ethical principles for AI are abundant. Principles that compile down to an envelope, a monitor and a constraint set are rare. Frameworks that make that connection explicit, from any intellectual tradition, have something to offer the field.

Civilian autonomy is under-tested. The attack surface SABER studies is already present in commercial drones and robotics. Independent, transparent red-teaming of civilian systems is an open niche.

• • •

Conclusion

CLARA and SABER are best read as two halves of one sentence: prove what you can, then attack what you proved. The proof tells you the boundary of trust. The attack tells you whether the boundary holds in the real world.

The AMANAH framing adds a third half that engineering alone tends to leave implicit: that autonomy is a delegated trust, not an inherent right. A system that knows the limits of its authority, watches itself continuously, and holds to fixed norms of conduct when uncertain is not merely safer. It is governable. That, rather than raw capability, is the property that will decide which autonomous systems are allowed to operate at all.

• • •

إِلٰهِي أَنْتَ مَقْصُودِي وَرِضَاكَ مَطْلُوبِي، أَعْطِنِي مَحَبَّتَكَ وَمَعْرِفَتَكَ

Ilahi anta maqsudi wa ridhaka matlubi, a'tini mahabbataka wa ma'rifataka

Prepared by TXIO Fusion Solutions

Disclaimer: This document is prepared for research awareness purposes only. It is based on open-source reporting available as of the publication date, including official DARPA programme pages and published contract announcements, and may not reflect subsequent developments. It does not constitute policy, legal or investment advice. TXIO Fusion Solutions assumes no liability for decisions made on the basis of this document.

Sources

DARPA, "CLARA: Compositional Learning-And-Reasoning for AI Complex Systems Engineering" (programme page)

DARPA, "SABER: Securing Artificial Intelligence for Battlefield Effective Robustness" (programme page)

Military Embedded Systems, "AI assurance the aim of new DARPA program" (11 February 2026)

Military & Aerospace Electronics, "DARPA seeks high-assurance artificial intelligence proposals under CLARA program" (13 April 2026)

Military & Aerospace Electronics, "Lockheed Martin, BAE to defend military AI from data poisoning and cyber attack" (12 March 2026)

Kitware, "Kitware Awarded $4M DARPA SABER Contract to Evaluate AI-Enabled Battlefield Systems" (4 May 2026)

EverGlade Consulting, "DARPA Launches SABER Initiative to Secure AI on the Battlefield" (17 February 2025)