arXiv AI
Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 15
A Three-Axis Stress Test of LLM vs Classical ML for Network Intrusion Detection under Distribution Shift and Adversarial Evasion
The study compares XGBoost and RoBERTa‑LoRA for network intrusion detection across three evaluation axes: same‑dataset performance, cross‑dataset transfer, and adversarial evasion. Both models perform similarly on the same dataset, but XGBoost outperforms RoBERTa‑LoRA by 15 F1 points and 25 balanced accuracy points when transferred to a different network, while RoBERTa‑LoRA wins by about 17 F1 points under adversarial evasion. Feature‑leakage ablation shows that cross‑dataset transfer improvements are non‑monotonic and directional, suggesting leakage is spread across features rather than isolated. "whyItMatters":"The findings demonstrate that a model’s superiority depends on the specific robustness axis evaluated, underscoring the need for multi‑axis, multi‑metric testing in network intrusion detection research."
arXiv AI
Jun 9
The Confidence Trap: Calibration Attacks for Graph Neural Networks
arXiv:2606. 08467v1 Announce Type: cross Abstract: While confidence calibration is essential for trustworthy decision-making in safety-critical applications, the robustness of calibrated GNNs to adversarial structural perturbations remains largely unexplored.
arXiv AI
Jun 29
Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection
arXiv:2606. 28134v1 Announce Type: cross Abstract: Graph-based fraud detection is essential for safeguarding large-scale transaction systems, where undetected anomalies may lead to substantial financial losses and security risks.
arXiv AI
Sep 24
Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
The paper introduces FedMAST, a Federated Multi‑Axis Structural Tracing defense designed to detect and contain backdoor attacks in federated learning. FedMAST evaluates client updates through complementary structural, spectral, and historical evidence, applying tiered filtering and round‑level containment. In experiments across six backdoor attacks, FedMAST consistently achieves lower attack success rates while preserving high main‑task accuracy.
arXiv Machine Learning
Oct 9
Evi-VN: Hard Region Guided Virtual Node Evidence Injection for GNN-Based Fraud Detection
Evi-VN is a new framework for graph neural network (GNN) fraud detection that injects evidence from diverse modalities—structured records, text, images, and audio—into virtual node representations. It targets shared hard regions where standard GNNs fail to distinguish well‑disguised fraudsters from legitimate users, correcting blind spots without disrupting reliable predictions. Experiments on bot, fake‑review, refund‑evidence, and telecom‑fraud datasets demonstrate its effectiveness across generic, fraud‑specific, and unseen GNNs.
arXiv AI
Aug 14
Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection
arXiv:2608. 12441v1 Announce Type: cross Abstract: Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst receives a score but no reason.