NeuroTrace: Inference Provenance-Based Detection of Adversarial Examples

• URL: http://arxiv.org/abs/2604.14457v1
• Date: Wed, 15 Apr 2026 22:23:40 GMT
• Title: NeuroTrace: Inference Provenance-Based Detection of Adversarial Examples
• Abstract summary: We introduce NeuroTrace, a framework for analyzing inference provenance through Inference Provenance Graphs (IPGs)<n>IPGs are heterogeneous graphs that capture both activation behavior and parameter-induced dataflow during a model's forward pass.<n>We evaluate IPG-based detectors for adversarial example detection under intra-attack, multi-attack, and cross-threat transfer settings.
• Score: 1.096626056612224
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks (DNNs) remain largely opaque at inference time, limiting our ability to detect and diagnose malicious input manipulations such as adversarial examples. Existing detection methods predominantly rely on layer-local signals (e.g., activations or attribution scores), leaving cross-layer information flow and execution structure under-explored. We introduce NeuroTrace, a framework and open dataset for analyzing inference provenance through Inference Provenance Graphs (IPGs). IPGs are heterogeneous graphs that capture both activation behavior and parameter-induced dataflow during a model's forward pass, providing a structured representation of how information propagates through the network. NeuroTrace includes (i) a reproducible extraction engine that instruments model execution, (ii) a standardized graph representation compatible with heterogeneous GNNs, and (iii) a benchmark suite spanning multiple adversarial attack families across vision and malware domains. Using this framework, we evaluate IPG-based detectors for adversarial example detection under intra-attack, multi-attack, and cross-threat transfer settings. Our results show that inference provenance provides a strong and transferable signal for distinguishing adversarial and benign inputs, achieving consistently high detection performance and improving over prior graph-based baselines. We further analyze the conditions under which provenance-based detection generalizes across attack types, as well as the associated runtime and storage trade-offs. By releasing the dataset, extraction pipeline, and evaluation protocol, NeuroTrace enables systematic study of inference-time behavior and establishes inference provenance as a practical foundation for building more transparent and auditable machine learning systems.

Related papers

• Cognitive Graph Intelligence for Adaptive and Robust DDoS Attack Detection in Next Generation Networks [2.434167379974669]
  This paper proposes a Graph-based Generative Adrial Network (GraphGAN) that serves as the cognitive detection engine for this task.<n>GraphGAN captures the relational structure among traffic flows while addressing imbalance through adversarial generation of synthetic samples.<n>The generator learns the distribution of DDoS attacks to synthesize realistic minority samples, while a Graph Convolutional Network (GCN)-based discriminator distinguishes real from synthetic graph data.
  arXiv  Detail & Related papers  (2026-08-18T04:18:31Z)
• An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation [2.0740117800511215]
  Auto-Prov is an end-to-end framework for provenance graph-based anomaly detectors.<n>It clusters unseen log types and efficiently extracts provenance edges and entity-level information.<n>It infers system-level functional context for both known and previously unseen system entities.<n>It produces stable, interpretable attack summaries that remain robust under system evolution.
  arXiv  Detail & Related papers  (2026-03-17T19:40:05Z)
• Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection [51.93878677594561]
  In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data.<n>We propose a Policy-Guided Outlier Synthesis framework that replaces statics with a learned exploration strategy.
  arXiv  Detail & Related papers  (2026-02-28T11:40:18Z)
• Graph Enhanced Trajectory Anomaly Detection [23.8160784400789]
  Trajectory anomaly detection is essential for identifying unusual and unexpected movement patterns in applications ranging from intelligent transportation systems to urban safety and fraud prevention.<n>Existing methods only consider limited aspects of the trajectory nature and its movement space by treating trajectories as sequences of sampled locations.<n>The proposed Graph Enhanced Trajectory Anomaly Detection framework tightly integrates road network topology, segment semantics, and historical travel patterns to model trajectory data.
  arXiv  Detail & Related papers  (2025-09-22T20:15:15Z)
• Out-of-Distribution Detection on Graphs: A Survey [58.47395497985277]
  Graph out-of-distribution (GOOD) detection focuses on identifying graph data that deviates from the distribution seen during training.<n>We categorize existing methods into four types: enhancement-based, reconstruction-based, information propagation-based, and classification-based approaches.<n>We discuss practical applications and theoretical foundations, highlighting the unique challenges posed by graph data.
  arXiv  Detail & Related papers  (2025-02-12T04:07:12Z)
• Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection [15.757864894708364]
  Graph anomaly detection plays a crucial role in identifying exceptional instances in graph data that deviate significantly from the majority. We propose a novel few-shot Graph Anomaly Detection model called FMGAD. We show that FMGAD can achieve better performance than other state-of-the-art methods, regardless of artificially injected anomalies or domain-organic anomalies.
  arXiv  Detail & Related papers  (2023-11-17T07:49:20Z)
• Combating Bilateral Edge Noise for Robust Link Prediction [56.43882298843564]
  We propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse. Two instantiations, RGIB-SSL and RGIB-REP, are explored to leverage the merits of different methodologies. Experiments on six datasets and three GNNs with diverse noisy scenarios verify the effectiveness of our RGIB instantiations.
  arXiv  Detail & Related papers  (2023-11-02T12:47:49Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Unsupervised Abnormal Traffic Detection through Topological Flow Analysis [1.933681537640272]
  topological connectivity component of a malicious flow is less exploited. We present a simple method that facilitate the use of connectivity graph features in unsupervised anomaly detection algorithms.
  arXiv  Detail & Related papers  (2022-05-14T18:52:49Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• DNS Covert Channel Detection via Behavioral Analysis: a Machine Learning Approach [0.09176056742068815]
  We propose an effective covert channel detection method based on the analysis of DNS network data passively extracted from a network monitoring system. The proposed solution has been evaluated over a 15-day-long experimental session with the injection of traffic that covers the most relevant exfiltration and tunneling attacks.
  arXiv  Detail & Related papers  (2020-10-04T13:28:28Z)
• Graph Backdoor [53.70971502299977]
  We present GTA, the first backdoor attack on graph neural networks (GNNs) GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features. It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
  arXiv  Detail & Related papers  (2020-06-21T19:45:30Z)

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.