Search papers, labs, and topics across Lattice.
This paper introduces a decision-contract theory framework for automated security decisions, focusing on the structural aspects of risk certification. By analyzing the relationship between decision inputs, outputs, and their correctness, the authors reveal how errors can be redistributed among automation, human intervention, and semantic masking. The empirical results demonstrate that their approach maintains acceptable false-attribution risk across various configurations, achieving 90.3% compliance with target risk levels and 83.4% mean correct automation in LLM-based intrusion detection scenarios.
Automated security decisions can achieve over 90% compliance with risk targets while maintaining high automation accuracy through a novel decision-contract theory.
An unconditional risk bound on automated decisions can be satisfied without automating anything, since a selector that never acts drives the bound to zero. We show this is structural: any risk certificate is defined over a decision contract, the inputs a system acts on plus the semantic relation under which an output counts correct, and weakening either hides base-classifier error. We develop a decision-contract theory: an error-conservation law showing error is only reassigned among harmful automation, human deferral, and semantic masking; a label-free singleton capacity certifying structural incapacity, with a risk-feasible refinement separating recoverable threshold misalignment from risk-constrained incapacity; and a non-degenerate actionability certificate excluding all-abstain solutions by construction. We instantiate this on ATT\&CK-aligned alert triage for LLM-based intrusion detection, the setting that exposed the vacuity failure. Across 3 IDS datasets, 6 LLMs, and 4 error-rate thresholds, empirical false-attribution risk stays at or below target in 90.3% of configurations, with 83.4% mean correct automation. The capacity diagnostic explains every low-utility configuration; its refinement separates genuine misalignment from risk-constrained incapacity, confirmed by an exhibited alternative threshold; a training-stability re-run finds no confirmed structural-incapacity instance; and real fine-grained attack-subtype labels confirm the coarsening-transfer identity under a genuine many-to-one map, with small but non-zero masking mass.
