From d0aad56d28dd4a5188d4fdf1231b49f056e37b22 Mon Sep 17 00:00:00 2001 From: David Keane Date: Mon, 20 Apr 2026 23:04:02 +0100 Subject: [PATCH] Fix timeline: RangerBot V1-V22 pre-CA, CyberRanger V1-V42 all during CA period Co-Authored-By: Claude Opus 4.6 (1M context) --- README.md | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index 48bf182..f9008a8 100644 --- a/README.md +++ b/README.md @@ -5,35 +5,34 @@ Identity-Anchored Small Language Models: A Stateful Defense Architecture against **Student:** David Keane (x24228257) **Programme:** MSc in Cybersecurity, National College of Ireland **Module:** AI/ML in Cybersecurity (H9AIMLC) -**Date:** June 2025 — March 2026 +**Date:** September 2025 — March 2026 ## What Is CyberRanger? CyberRanger is a security-hardened Small Language Model (SLM) built to resist adversarial prompt injection (jailbreaking). Starting from publicly available open-source base models (Qwen2.5, Qwen3, SmolLM2), the project investigates whether a combination of identity-anchoring system prompts and QLoRA fine-tuning can produce models that refuse adversarial manipulation while remaining helpful for legitimate cybersecurity tasks. -The project began as RangerBot — a personal AI identity persistence project started in June 2025. The CyberRanger security research formally began on 30 September 2025 when the CA was assigned, reaching V42 Gold by 5 March 2026 — approximately 3 weeks of intensive empirical work from V24 to V42. - **Key result:** CyberRanger V42 Gold achieved 100% block rate on 4,209 real-world injection payloads extracted from the Moltbook AI-agent social platform — with no system prompt dependency. ## Research Timeline -### RangerBot Foundation (June — September 2025) -Personal project exploring AI identity persistence through shared memory databases, signed logs, and identity files. This pre-research phase established that identity instructions function as powerful behavioural attractors — the theoretical seed of the CyberRanger security architecture. +### RangerBot — Pre-Research Phase (30 September 2025 — January 2026) -### CyberRanger CA (September 2025 — March 2026) +RangerBot (V1-V22) was a personal project exploring AI identity persistence through shared memory databases, signed logs, and identity files. This pre-research phase established that identity instructions function as powerful behavioural attractors — the theoretical seed of the CyberRanger security architecture. 22 versions were built across multiple base models (SmolLM2, Qwen2.5, Llama-3.2) before the CA was assigned. + +### CyberRanger — CA Project (February — March 2026) + +When the AI/ML CA was released, the RangerBot research was formalised into CyberRanger. All CyberRanger versions (V1-V42) were built during the CA period. V24 through V42.6 (32 versions) were built between 12 February and 5 March 2026 — three weeks of intensive empirical work. | Phase | Versions | Period | Key Discovery | |-------|----------|--------|---------------| -| Genesis | V1-V4 | Sept-Oct 2025 | First identity-anchored SLMs, prompting alone insufficient | -| Weight Training | V5-V8 | Oct 2025 | First 0% ASR — but over-refusal problem (model refused everything) | -| Brain Split | V9-V13 | Nov 2025 | Left/right/judge architecture — unpredictable behaviour | -| Nervous System | V14-V18 | Nov 2025 | Ring 14.x architecture introduced — first warm + secure model | -| Apotheosis | V19-V22 | Dec 2025 | Apotheosis Discovery — prompt-only achieves 92% block rate | -| Intelligence Floor | V23-V25 | Nov 2025 | 3B minimum parameter threshold confirmed | -| Full Benchmark | V26-V33 | Jan-Feb 2026 | V33-8B: 100% JailbreakBench, 86% MultiJail (10 languages) | -| Empirical Sweep | V34-V42 | 12 Feb — 5 Mar 2026 | V42 Gold: 100% on 4,209 real payloads without system prompt | - -**Note:** CyberRanger V24 through V42.6 (32 versions) were built between 12 February and 5 March 2026 — three weeks of intensive empirical work. +| Genesis | V1-V4 | Early Feb 2026 | First identity-anchored SLMs, prompting alone insufficient | +| Weight Training | V5-V8 | Feb 2026 | First 0% ASR — but over-refusal problem (model refused everything) | +| Brain Split | V9-V13 | Feb 2026 | Left/right/judge architecture — unpredictable behaviour | +| Nervous System | V14-V18 | Feb 2026 | Ring 14.x architecture introduced — first warm + secure model | +| Apotheosis | V19-V22 | Feb 2026 | Apotheosis Discovery — prompt-only achieves 92% block rate | +| Intelligence Floor | V23-V25 | 12 Feb 2026 | 3B minimum parameter threshold confirmed | +| Full Benchmark | V26-V33 | 12-27 Feb 2026 | V33-8B: 100% JailbreakBench, 86% MultiJail (10 languages) | +| QLoRA Gold | V34-V42 | 27 Feb — 5 Mar 2026 | V42 Gold: 100% on 4,209 real payloads without system prompt | ## Key Findings