Defense Systems
Pre-revenueIncubating

अभेद्यAbhedya

Sovereign defence systems that run at the edge.

Sovereign defence systems that run at the edge. अभेद्य (Abhedya — Sanskrit for the “impenetrable,” the indivisible) fields a single secure console, Arsenal Command, over a family of RSN-powered capabilities for police, intelligence and defence: on-device CDR & tower-dump forensics (Sanjaal), rhythm-biometric access control (Dwaar), field-adaptive recognition, GPS-denied navigation, and more. Everything is computed on the agency’s own machine — no cloud, link-survivable, auditable — so sensitive case data never leaves the room.

Visit Abhedyaabhedya.aiteleresearch.com
Since 2026Co-owned · commons ≤ 40%
§ 01

Research

From the Defense Systems Lab.

  • In preparation · JUN 18, 2026
    Training-Free Archetype Typing of Conspiracy Networks from Call-Detail Records — and the Limits of Structure-Only Detection

    We study an on-device, training-free classifier that types a multi-suspect call-detail-record (CDR) group by the clandestine-network archetype it most resembles — one of nineteen documented topologies — or as benign. Each archetype is a synthesised neuron: the measured feature-space centroid of canonical exemplars, scored by a uniform-weight Gaussian kernel in standardised space. On a replicated synthetic benchmark (8 runs, seeds disjoint from calibration), 20-class typing reaches 86.3% top-1 accuracy (95% CI 85.8–86.8%), macro-F1 0.856; an open-set abstention gate lifts selective accuracy to 88.5% at 95.0% coverage. The central result is negative and we lead with it: the risk score that separates conspiracies from a trivial benign null at AUC 1.00 separates them from realistic benign-but-busy groups (families, call-centres, rallies, fleets, carpools) at AUC 0.25 — below chance — flagging 83% of lawful cohesive groups. Structure does not encode intent. Accuracy falls from 83.8% to 33.3% under realistic partial observation. The defensible role is a structure-typer and lead-generator for a human analyst, not an autonomous detector; the benchmark is synthetic (separability and robustness, not field validation). The research substrate beneath the CDR-intelligence arm of अभेद्य (Abhedya).

  • In preparation · JUN 16, 2026
    Training-Free Cohort-Relative Keystroke-Cadence Verification: an Honest Benchmark Study

    We present a keystroke-cadence verifier for high-assurance login, synthesised in closed form from enrolment data — no gradient training, no epochs. Each sample becomes a fixed-length timing vector; the model z-score-normalises, removes incoherent enrolment samples, optionally Fisher-weights features, forms PCA sub-prototypes, and decides by a cohort-relative weighted-cosine margin gated by a per-user threshold. On the public CMU benchmark (51 subjects, held-out impostors) it attains mean per-subject EER 9.38% (7.78% with Fisher disabled) — in the range of the best detector of Killourhy & Maxion (≈9.62%), though not a head-to-head comparison (the cohort-relative protocol uses the other subjects as negative evidence; σ≈8.5%, 95% CI [7.0, 11.7]%). A full ablation — including a negative result — shows cohort-relative scoring alone sets a low-false-accept operating point (FAR 0.69% vs 13.3% for an unweighted single-threshold baseline, ≈19× fewer impostor admissions); per-user adaptive thresholds were inert on this benchmark; Fisher weighting slightly hurts. Password-gated continuous learning closes cross-session drift without any false-accept cost. The synthetic study is a consistency check, not independent field evidence; only zero-effort impostors are evaluated. A behavioural-biometric instance of the RSN line; the research substrate beneath the rhythm-based access layer of अभेद्य (Abhedya).

§ 02

Releases

From the Defense Systems Lab.

  • software · beta · JUN 18, 2026
    Dwaar Rhythm Login v1

    Behavioural login for Abhedya's Arsenal Command — an operator types a public phrase and the key is their keystroke rhythm, verified against the enrolled cohort, with a passphrase fallback.

§ 03

Defense Systems Lab

AI that holds when the link doesn't.

Edge-resident, link-survivable, auditable AI for the sovereign defence of the realm — recognition, anomaly and network-structure analysis that run on the device itself, offline, and explain why. Built on the RSN line so a model can be re-tuned in the field with no GPU and no cloud, and every call is one a human can audit. It is the research substrate beneath अभेद्य (Abhedya).

About the lab →