Imagen de Portada

GESR: Graph-Based Edge Semantic Reconstruction for Stealthy Communication Detection with Benign-Only Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Henghui, Zhang, Yuchen, Ma, Xiaobo
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs
por: Luo, Qi, et al.
Publicado: (2026)

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
por: Wang, Xiaobao, et al.
Publicado: (2025)

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
por: Tan, Yuting, et al.
Publicado: (2025)

Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning
por: Lyu, Xiaoting, et al.
Publicado: (2024)

The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
por: Hao, Yifan, et al.
Publicado: (2024)

IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systems
por: Zhang, Yuchen, et al.
Publicado: (2026)

SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
por: Xu, Haotian, et al.
Publicado: (2025)

Stealing Training Graphs from Graph Neural Networks
por: Lin, Minhua, et al.
Publicado: (2024)

Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
por: Lu, Jiacheng, et al.
Publicado: (2026)

Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models
por: Zhang, Yiyang, et al.
Publicado: (2026)

Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
por: Trong, Thua Huynh, et al.
Publicado: (2024)

MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment
por: Halloran, John
Publicado: (2025)

Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
por: Wang, Zhiwei, et al.
Publicado: (2024)

What Does Normal Even Mean? Evaluating Benign Traffic in Intrusion Detection Datasets
por: Wilkinson, Meghan, et al.
Publicado: (2025)

Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
por: Chanda, Dibaloke, et al.
Publicado: (2023)

Detecting Backdoor Attacks via Similarity in Semantic Communication Systems
por: Wei, Ziyang, et al.
Publicado: (2025)

Stealthy Imitation: Reward-guided Environment-free Policy Stealing
por: Zhuang, Zhixiong, et al.
Publicado: (2024)

Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
por: Liu, Xin, et al.
Publicado: (2024)

A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction
por: Wan, Jialin, et al.
Publicado: (2025)

SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
por: Choe, Minyeong, et al.
Publicado: (2024)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
por: Yan, Xinhai, et al.
Publicado: (2025)

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
por: Xie, Zhixin, et al.
Publicado: (2026)

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
por: Hsu, Chia-Yi, et al.
Publicado: (2026)

Identifying Obfuscated Code through Graph-Based Semantic Analysis of Binary Code
por: Cohen, Roxane, et al.
Publicado: (2025)

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
por: Guo, Ji, et al.
Publicado: (2026)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
por: Lou, Jiadong, et al.
Publicado: (2025)

Training Data Reconstruction: Privacy due to Uncertainty?
por: Runkel, Christina, et al.
Publicado: (2024)

Lorica: A Synergistic Fine-Tuning Framework for Advancing Personalized Adversarial Robustness
por: Qi, Tianyu, et al.
Publicado: (2025)

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
por: Yoon, Sangyeon, et al.
Publicado: (2024)

On the Query Complexity of Training Data Reconstruction in Private Learning
por: Mukherjee, Prateeti, et al.
Publicado: (2023)

LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding
por: Jia, Yifan, et al.
Publicado: (2025)

SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications
por: Wang, Weiqi, et al.
Publicado: (2025)

Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection
por: Dautartas, Juozas, et al.
Publicado: (2026)

Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training
por: Xu, Rongwu, et al.
Publicado: (2024)

SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
por: Xue, Eric, et al.
Publicado: (2025)

GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification
por: Buchta, Robin, et al.
Publicado: (2026)

Graph Reconstruction from Differentially Private GNN Explanations
por: Sahoo, Rishi Raj, et al.
Publicado: (2026)

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
por: Xu, Yuancheng, et al.
Publicado: (2024)

Towards Efficient Target-Level Machine Unlearning Based on Essential Graph
por: Xu, Heng, et al.
Publicado: (2024)

Wavelet-Aware Anomaly Detection in Multi-Channel User Logs via Deviation Modulation and Resolution-Adaptive Attention
por: Kong, Kaichuan, et al.
Publicado: (2026)