HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails

• URL: http://arxiv.org/abs/2608.08485v1
• Date: Sun, 09 Aug 2026 05:05:12 GMT
• Title: HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails
• Abstract summary: HoloAegis is a minimally parametric topological inference framework that decouples representation from reasoning.<n> evaluated across 8 benchmarks, HoloAegis achieves state-of-the-art accuracy (1.0000 AUC on AuthenHallu, 0.9802 on HarmBench), with sub-millisecond latency, zero cold-start data, and cross-lingual transfer (0.9758 AUC on Chinese CHIFRAUD)
• Score: 17.07949373919355
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inference costs. We challenge the prevailing paradigm by asking: can safety be achieved through pure geometric reasoning over frozen semantic representations? We present HoloAegis, a minimally parametric topological inference framework that decouples representation from reasoning. We term our approach minimally parametric because the only free parameters are the anchor count K and the temperature tau, both fixed after construction and requiring no gradient-based training. An un-fine-tuned encoder maps text to a unit sphere, after which all decisions are purely geometric. We formalize safety evaluation as a Gibbs-Boltzmann Free Energy computation over a pre-computed System Topology Anchor Bank, and we introduce Dual Time-Scale Exponential Moving Averages to detect progressive multi-turn semantic drift. Our key theoretical insight is a Topological Boundary Stability Conjecture: we provide theoretical motivation and strong empirical evidence that sparse anchor centroids stabilize the decision boundary against high-frequency lexical perturbations far better than full vector space methods. Evaluated across 8 benchmarks, HoloAegis achieves state-of-the-art accuracy (1.0000 AUC on AuthenHallu, 0.9802 on HarmBench) with sub-millisecond latency, zero cold-start data, and cross-lingual transfer (0.9758 AUC on Chinese CHIFRAUD).

Related papers

• Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems [40.47928908205563]
  Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection.<n>Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification.<n>We provide confidence gating for evaluation and re-anchoring guarantees for piecewise-stationary environments.<n>Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws.
  arXiv  Detail & Related papers  (2026-09-02T15:50:10Z)
• Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation [48.887627688666974]
  Learning dissipation rates in large-scale open quantum systems is a major obstacle for near-term quantum technologies.<n>Here, we propose a scalable noise-learning framework for Lindblad dissipation rates that combines a simulation method, the Jump Method (TJM)<n>We demonstrate the approach on two noise models in the Ising model, in which independent dissipation rates are learned for each site up to $N_mathrmsite=16$.<n>This combination of scalable numerics and rigorous theoretical guarantees positions TJM-based noise learning as a practical foundation for characterizing dissipation in large quantum devices.
  arXiv  Detail & Related papers  (2026-08-25T15:07:11Z)
• Trajectory-Anchor Optimization for Overconfident Thermal Visual Place Recognition: Zero-Leakage OOD Auditing and Kidnapped-Robot Recovery [3.9929096403817255]
  Trajectory-Anchor Optimization (TAO) is an efficient fail-safe filter at a macro-scale.<n>Within a 5m radius, hallucinations often possess a locally consistent geometry that deceives rigid alignment.<n>TAO establishes a distinct convergence basin (10m) where multi-view consistency reliably isolates catastrophic topological breaks.
  arXiv  Detail & Related papers  (2026-07-06T07:31:37Z)
• Latent Clarity: Bridging World-Model Kinematics to Semantic Manifolds for Video Anomaly Anticipation [0.0]
  Continuous video detection is dominated by reactive Multiple Instance Learning (MIL) that collapses into features into scores.<n>We introduce PULS (Predictive Unified Latent Space), a continuous semantic world-model pipeline.<n>This translation alone yields a chunk-level AUROC of 0.8994 for UCF-Crime and 0.8162 for out-of-distribution- anomaly without MIL or hierarchical fusion.
  arXiv  Detail & Related papers  (2026-07-03T18:47:54Z)
• Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance [48.34904668359272]
  Adrial attacks on large language models have limited practical impact despite extensive research.<n>We introduce Greedy Coordinate Diffusion (GCD), a novel framework that efficiently generates adversarial attacks against safety-aligned models.<n>GCD maintains low perplexity and high semantic adherence to the adversary's original intent.
  arXiv  Detail & Related papers  (2026-06-14T01:18:53Z)
• Graph Transfer Learning via Shared Latent Geometry: Theory and Applications [12.735610064958712]
  Inference and control in engineered physical systems pay a heavy physics cost at deployment.<n>We propose an asymmetric two-pathway architecture that resolves both issues.<n>A teacher encoder consumes privileged dense states from a high-fidelity simulator and represents the system through operator-polynomial features stable under spectral perturbation.<n>A student encoder learns the same latent geometry from sparse field data and operator descriptors.
  arXiv  Detail & Related papers  (2026-05-30T13:00:13Z)
• Controlling False Discovery in Arbitrarily Structured Hypothesis Spaces via Reproducing Kernels [47.16593717985932]
  We introduce a framework that unifies continuous domains, graphs, and hierarchies under a single algorithm through kernel choice alone.<n>We provide two decision rules which we prove to control the False Discovery Rate (FDR)<n>We validate our method on two sources: spatial locations derived from high-dimensional real-world datasets, and a differential gene expression task utilizing protein-protein interaction graphs.
  arXiv  Detail & Related papers  (2026-05-17T17:42:56Z)
• Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL [8.809468023364703]
  Design of robust reinforcement learning algorithms poses fundamental challenges.<n>We propose an approximate DRRL framework based on a first-order expansion of the relevant robust functional.<n>To learn the fixed point of this approximate equation, we propose Mean-Variance Approximation (MVSA)
  arXiv  Detail & Related papers  (2026-05-08T19:24:28Z)
• SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere [90.85001795656633]
  Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos.<n>We propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere.
  arXiv  Detail & Related papers  (2026-05-08T16:57:38Z)
• RANDSMAPs: Random-Feature/multi-Scale Neural Decoders with Mass Preservation [39.146761527401424]
  We introduce RANDSMAPs (Random-feature/multi-scale neural decoders with Mass Preservation) to solve the ill-posed pre-image problem in manifold learning.<n>We demonstrate that RANDSMAPs yield high reconstruction accuracy at low computational cost and maintain mass conservation at single-machine precision.
  arXiv  Detail & Related papers  (2026-01-21T09:18:10Z)
• Gradient Structure Estimation under Label-Only Oracles via Spectral Sensitivity [37.729118253160145]
  We develop a unified theoretical perspective showing that a wide range of existing sign-flipping hard-label attacks can be interpreted as implicitly approximating the sign of the true loss gradient.<n>Motivated by this first-principles understanding, we propose a new attack framework that combines a zero-query frequency-domain initialization with a Pattern-Driven Optimization (PDO) strategy.<n>We empirically validate our framework through extensive experiments on CIFAR-10, ImageNet, and ObjectNet, covering standard and adversarially trained models, commercial APIs, and CLIP-based models.
  arXiv  Detail & Related papers  (2026-01-17T02:47:47Z)
• Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition [41.77490816513839]
  We propose a novel method for zero-shot skeleton action recognition, termed $texttt$textbfFlora$$.<n>Specifically, we attune textual semantics by incorporating direction-aware regional semantics, and a cross-modal consistency objective.<n>Experiments on three benchmark datasets validate the effectiveness of our method, showing particularly impressive performance even when trained with only 10% of the seen data.
  arXiv  Detail & Related papers  (2025-11-12T14:54:53Z)
• Pure Exploration via Frank-Wolfe Self-Play [9.025261095806309]
  We study pure exploration in structured multi-armed bandits, aiming to efficiently identify the correct hypothesis from a finite set of alternatives.<n>Our analysis proceeds through a continuous-time steer: a differential inclusion with a Lyapunov function that decays, implying a vanishing duality gap and convergence to the optimal value.
  arXiv  Detail & Related papers  (2025-09-24T08:55:21Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)
• ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation [106.04777600352743]
  Differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. The single-path DARTS comes in, which only chooses a single-path submodel at each step. While being memory-friendly, it also comes with low computational costs. We propose a new algorithm called RObustifying Memory-Efficient NAS (ROME) to give a cure.
  arXiv  Detail & Related papers  (2020-11-23T06:34:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.