Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes

• URL: http://arxiv.org/abs/2608.24037v1
• Date: Tue, 25 Aug 2026 03:51:20 GMT
• Title: Curved Inference II: Sleeper Agent Geometry - Extending Interpretability Beyond Probes
• Abstract summary: This paper extends Anthropic's Sleeper Agents research, which showed artificial backdoors persist through safety training & can be detected by linear probes with >99% accuracy.<n>We introduce a naturalistic methodology using multi-turn context windows that simulates realistic deceptive reasoning without artificial triggers or supervised backdoor insertion.<n> Geometric structure reliably predicts semantic classification, with statistically significant differences in surface area across five prompt strategies & two model families.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This paper extends Anthropic's Sleeper Agents research [1], which showed artificial backdoors persist through safety training & can be detected by linear probes with >99% accuracy [2]. However, probe-based detection relies on linear separability that may be an artefact of backdoor insertion rather than a property of naturally occurring deceptive alignment. Sophisticated deceptive behaviours emerging through natural training are unlikely to produce such convenient linear signals. We introduce a naturalistic methodology using multi-turn context windows that simulates realistic deceptive reasoning without artificial triggers or supervised backdoor insertion. Rather than binary trigger-response patterns, we examine how semantic complexity emerges through gradual context development. Building on our Curved Inference framework, we analyse curvature, salience, & introduce semantic surface area (A'), a new metric of representational work capturing both the magnitude & directional change of meaning construction in unnormalised residual space. Without backdoors, labels, or probes, we apply this framework to naturalistic deceptive prompts & classify model outputs via LLM consensus. Geometric structure reliably predicts semantic classification, with statistically significant differences in surface area across five prompt strategies & two model families. Critically, measurement precision can reveal geometric signatures hidden by classification noise - some strategies improve from non-significant (p = 0.555) to significant (p = 0.048). This validates that sophisticated reasoning creates intrinsic geometric patterns that persist even when detection appears to fail, suggesting the shape of inference itself encodes semantic patterns regardless of whether models have learned to suppress linear indicators of deception - a scalable, unsupervised path for detection when linear methods fail.

Related papers

• Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection [58.25418970608328]
  We study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains.<n>Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution.<n>We propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem.
  arXiv  Detail & Related papers  (2026-07-08T09:27:15Z)
• Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators [51.771100367755544]
  We introduce a geometric perspective to address the mismatch between the inductive bias of existing methods and the structure of the data.<n>Specifically, we learn a projection operator onto the manifold of normal samples and define a sample as anomalous if it is altered by this projection.<n> Notably, it provides a unifying interpretation of reconstruction-based methods by explaining their success and failure in terms of projection quality.
  arXiv  Detail & Related papers  (2026-06-13T12:37:20Z)
• Need We Teach Foundation Models What is a Generative Image? Gradient-Free Generative Artifact Detection via Analytic Spectral Adaptation [3.881211374324378]
  Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.<n>We propose a gradient-free methodology reframing detection from binary classification to an out-of-distribution (OOD) anomaly measurement problem.
  arXiv  Detail & Related papers  (2026-06-03T13:04:23Z)
• A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning [52.452902154360565]
  We introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning.<n>MCBP explicitly models the intrinsic curvature of the data manifold and computes pointwise mean curvature without requiring principled manifold parametrization.<n>Experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance.
  arXiv  Detail & Related papers  (2026-05-05T20:19:09Z)
• Representational Curvature Modulates Behavioral Uncertainty in Large Language Models [7.361948338002342]
  temporal straightening offers an account of how the next-token prediction objective shapes representations.<n>In large language models (LLMs), temporal straightening offers an account of how the next-token prediction objective shapes representations.<n>We provide such a link by relating contextual curvature-a geometric measure of how sharply the representational trajectory bends over recent context-to next-token entropy.
  arXiv  Detail & Related papers  (2026-04-27T03:00:47Z)
• Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning [13.891913455492697]
  We argue that a core obstacle to a general, structural-assumption-free approach is the lack of an equivalence characterization.<n>Key to our approach is a new tool, edge rank constraints, which fills a missing piece in the toolbox for latent-variable causal discovery.
  arXiv  Detail & Related papers  (2026-03-05T03:57:14Z)
• Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
  We propose a unified backdoor detection framework in the semi-honest setting.<n>Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.<n> Notably, it is the first to effectively detect backdoors in multimodal large language models.
  arXiv  Detail & Related papers  (2025-03-21T06:12:06Z)
• Learning nonparametric latent causal graphs with unknown interventions [18.6470340274888]
  We establish conditions under which latent causal graphs are nonparametrically identifiable. We do not assume the number of hidden variables is known, and we show that at most one unknown intervention per hidden variable is needed.
  arXiv  Detail & Related papers  (2023-06-05T14:06:35Z)
• Score-based Causal Representation Learning with Interventions [54.735484409244386]
  This paper studies the causal representation learning problem when latent causal variables are observed indirectly. The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
  arXiv  Detail & Related papers  (2023-01-19T18:39:48Z)
• ContraFeat: Contrasting Deep Features for Semantic Discovery [102.4163768995288]
  StyleGAN has shown strong potential for disentangled semantic control. Existing semantic discovery methods on StyleGAN rely on manual selection of modified latent layers to obtain satisfactory manipulation results. We propose a model that automates this process and achieves state-of-the-art semantic discovery performance.
  arXiv  Detail & Related papers  (2022-12-14T15:22:13Z)
• Classification and Adversarial examples in an Overparameterized Linear Model: A Signal Processing Perspective [10.515544361834241]
  State-of-the-art deep learning classifiers are highly susceptible to infinitesmal adversarial perturbations. We find that the learned model is susceptible to adversaries in an intermediate regime where classification generalizes but regression does not. Despite the adversarial susceptibility, we find that classification with these features can be easier than the more commonly studied "independent feature" models.
  arXiv  Detail & Related papers  (2021-09-27T17:35:42Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)

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.