Evolving and Detecting Multi-Turn Deception using Geometric Signatures

• URL: http://arxiv.org/abs/2605.27671v1
• Date: Tue, 26 May 2026 20:48:33 GMT
• Title: Evolving and Detecting Multi-Turn Deception using Geometric Signatures
• Abstract summary: Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts.<n>We present a unified pipeline that generates realistic multi-turn deceptive question sets.<n>Using this data, we were able to detect deceptive attempts to access prohibited information.
• Score: 1.160208922584163
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect, multi-turn probing. To defend against this more nuanced form of deception, we present a unified pipeline that generates realistic multi-turn deceptive question sets via multi-objective genetic prompt optimization with co-evolving mutation operators. We validate this dataset through a human study, which also revealed that early generations yielded the most convincing deception and practical constraints such as adherence filtering and ordering effects. Using this data, we were able to detect deceptive attempts to access prohibited information using simple, explainable geometric signals in embedding space coupled with a lightweight feed-forward classifier. Three geometric features (angular coverage, distance ratio, and linearity) augmented with pairwise similarity statistics led to a compact predictive model that achieved consistently high recall (0.89) across base, reworded, and truncated (three-turn) scenarios, with test-time F1 ranging from 0.74-0.86. The results support a central hypothesis that multi-turn deceptive intent leaves a stable geometric footprint that enables lightweight, transparent screening without expensive end-to-end training. We further discuss responsible uses, limitations, and paths toward larger, more diverse human-evaluated datasets. The primary contribution to artificial intelligence is the multi-objective evolutionary framework for prompt generation, and the engineering application is the deployment of a lightweight geometric detection system for LLM safety infrastructure.

Related papers

• Latent Fact-Checking: Detecting Misinformation through Activation Engineering [1.3299946892361476]
  We introduce a misinformation detection framework grounded in activation engineering.<n>Our approach elicits a misinformation direction in the residual stream by contrasting activations from paired truthful and false statements.<n>We evaluate the method across 11 models on three fact-checking benchmarks: AVeriTeC, LIAR, and FACTors.
  arXiv  Detail & Related papers  (2026-08-05T18:00:14Z)
• Does Appearance Help? A Systematic Study of Image-Based Re-Identification in Online 3D Multi-Pedestrian Tracking [0.6117371161379209]
  This work presents a systematic study of image-based ReID in online 3D MOT, utilizing a lightweight projection-based framework.<n>Experiments on the Pedestrian class of the KITTI dataset reveal that naive linear fusion, of appearance and motion costs, degrades performance due to visual noise.<n>We show that lightweight architectures can offer an optimal trade-off between the low latency required for safe navigation and the discriminative power needed for social awareness.
  arXiv  Detail & Related papers  (2026-06-05T13:00:04Z)
• AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution [61.593935260052795]
  Post-training viaSupervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs)<n>Existing paradigms often reach a performance bottleneck due to the limitations of static data.<n>We propose Anchor Evolution (AnE), a new paradigm that integrates truth-anchored data curation and model evolution.
  arXiv  Detail & Related papers  (2026-05-25T08:26:34Z)
• Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling [12.573852448122716]
  Text-to-image (T2I) diffusion models have achieved remarkable success in image synthesis, but their reliance on large-scale data and open ecosystems introduces serious backdoor security risks.<n>Existing defenses, particularly input-level methods, are more practical for deployment but often rely on observable anomalies that become unreliable under stealthy, semantics-preserving trigger designs.<n>We propose SET, an input-level backdoor detection framework that constructs response-offset features under multi-scale perturbations and learns a compact benign response space from a small set of clean samples.
  arXiv  Detail & Related papers  (2026-04-14T08:31:37Z)
• A Synthetic Conversational Smishing Dataset for Social Engineering Detection [0.0]
  This paper presents a dataset of 3,201 labeled multi-round conversations designed to emulate realistic conversational smishing attacks.<n>Results show that TF-IDF-based models consistently outperform those using engineered features alone.
  arXiv  Detail & Related papers  (2026-04-13T17:26:17Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• Deep Learning Models for Robust Facial Liveness Detection [56.08694048252482]
  This study introduces a robust solution through novel deep learning models addressing the deficiencies in contemporary anti-spoofing techniques.<n>By innovatively integrating texture analysis and reflective properties associated with genuine human traits, our models distinguish authentic presence from replicas with remarkable precision.
  arXiv  Detail & Related papers  (2025-08-12T17:19:20Z)
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [81.93945602120453]
  We introduce an approach that is both general and parameter-efficient for face forgery detection.<n>We design a forgery-style mixture formulation that augments the diversity of forgery source domains.<n>We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)

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.