Search papers, labs, and topics across Lattice.
ClawdGo is introduced as a framework for training autonomous AI agents to recognize and reason about security threats endogenously, without modifying the underlying model. The framework incorporates a Three-Layer Domain Taxonomy (TLDT) to organize trainable dimensions, an Autonomous Security Awareness Training (ASAT) self-play loop, Cross-Session Memory Accumulation (CSMA), and formalization of the Security Awareness Calibration Problem (SACP). Experiments demonstrate that weakest-first ASAT significantly improves the agent's threat awareness, with CSMA ensuring persistent skill gains across sessions.
Forget external firewalls – ClawdGo teaches AI agents to spot and fend off attacks from the inside, boosting their security smarts by 20% through self-play.
Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framework for endogenous security awareness training: we teach the agent to recognise and reason about threats from the inside, at inference time, with no model modification. Four contributions are introduced: TLDT (Three-Layer Domain Taxonomy) organises 12 trainable dimensions across Self-Defence, Owner-Protection, and Enterprise-Security layers; ASAT (Autonomous Security Awareness Training) is a self-play loop where the agent alternates attacker, defender, and evaluator roles under weakest-first curriculum scheduling; CSMA (Cross-Session Memory Accumulation) compounds skill gains via a four-layer persistent memory architecture and Axiom Crystallisation Promotion (ACP); and SACP (Security Awareness Calibration Problem) formalises the precision-recall tradeoff introduced by endogenous training. Live experiments show weakest-first ASAT raises average TLDT score from 80.9 to 96.9 over 16 sessions, outperforming uniform-random scheduling by 6.5 points and covering 11 of 12 dimensions. CSMA retains the full gain across sessions; cold-start ablation recovers only 2.4 points, leaving a 13.6-point gap. E-mode generates 32 TLDT-conformant scenarios covering all 12 dimensions. SACP is observed when a heavily trained agent classifies a legitimate capability assessment as prompt injection (30/160).
