Imagen de Portada

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Fan, Xu, Binyan, Tang, Di, Zhang, Kehuan
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
por: Xu, Binyan, et al.
Publicado: (2025)

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
por: Xu, Binyan, et al.
Publicado: (2025)

Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection
por: Yang, Fan, et al.
Publicado: (2026)

Attackers Strike Back? Not Anymore -- An Ensemble of RL Defenders Awakens for APT Detection
por: Benabderrahmane, Sidahmed, et al.
Publicado: (2025)

BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator
por: Zhang, Ruyi, et al.
Publicado: (2026)

Your Agent Can Defend Itself against Backdoor Attacks
por: Changjiang, Li, et al.
Publicado: (2025)

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
por: Wang, Yifei, et al.
Publicado: (2026)

BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
por: Zhang, Andy K., et al.
Publicado: (2025)

Uplifted Attackers, Human Defenders: The Cyber Offense-Defense Balance for Trailing-Edge Organizations
por: Murphy, Benjamin, et al.
Publicado: (2025)

Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
por: Obioma, Chibueze Peace, et al.
Publicado: (2025)

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP
por: Xu, Binyan, et al.
Publicado: (2025)

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
por: Jin, Haotian, et al.
Publicado: (2025)

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
por: De Muri, Giovanni, et al.
Publicado: (2025)

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
por: Li, Siyuan, et al.
Publicado: (2026)

Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
por: Zhang, Yujie, et al.
Publicado: (2024)

Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing
por: Fan, Kaisheng, et al.
Publicado: (2026)

The Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers
por: Mengara, Orson
Publicado: (2024)

Backdoor Graph Condensation
por: Wu, Jiahao, et al.
Publicado: (2024)

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
por: Bullwinkel, Blake, et al.
Publicado: (2026)

Invisible Textual Backdoor Attacks based on Dual-Trigger
por: Hou, Yang, et al.
Publicado: (2024)

Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense
por: Zhou, Qi, et al.
Publicado: (2024)

ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
por: Yang, Feiyu, et al.
Publicado: (2025)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
por: Jiang, Peihai, et al.
Publicado: (2025)

Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
por: Tong, Terry, et al.
Publicado: (2024)

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
por: Zhang, Yuxiang, et al.
Publicado: (2024)

FedDefender: Backdoor Attack Defense in Federated Learning
por: Gill, Waris, et al.
Publicado: (2023)

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
por: Lin, Chenhao, et al.
Publicado: (2025)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
por: Liu, Qin, et al.
Publicado: (2023)

Backdoor defense, learnability and obfuscation
por: Christiano, Paul, et al.
Publicado: (2024)

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
por: Li, Ding, et al.
Publicado: (2024)

Backdoor Attack with Invisible Triggers Based on Model Architecture Modification
por: Ma, Yuan, et al.
Publicado: (2024)

Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering
por: Lyu, Xingyu, et al.
Publicado: (2025)

Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm
por: Pang, Yan, et al.
Publicado: (2025)

Invisible Backdoor Attack Through Singular Value Decomposition
por: Chen, Wenmin, et al.
Publicado: (2024)

Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
por: Wei, Jiali, et al.
Publicado: (2026)

Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain
por: Huang, Yuanmin, et al.
Publicado: (2025)

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
por: Zheng, Jingyi, et al.
Publicado: (2024)

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
por: Gong, Chen, et al.
Publicado: (2022)

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses
por: Pawlak, Stanisław, et al.
Publicado: (2025)

On the Consistency of GNN Explanations for Malware Detection
por: Shokouhinejad, Hossein, et al.
Publicado: (2025)