Copertina

AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Jiate, Wang, Binghui
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
di: Li, Jiate, et al.
Pubblicazione: (2025)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
di: Li, Jiate, et al.
Pubblicazione: (2025)

Graph Neural Network Explanations are Fragile
di: Li, Jiate, et al.
Pubblicazione: (2024)

Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
di: Li, Jiate, et al.
Pubblicazione: (2024)

Defending against Backdoor Attack on Deep Neural Networks
di: Cheng, Hao, et al.
Pubblicazione: (2020)

Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
di: Torpmann-Hagen, Birk, et al.
Pubblicazione: (2025)

Watermarking Graph Neural Networks via Explanations for Ownership Protection
di: Downer, Jane, et al.
Pubblicazione: (2025)

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
di: Hu, Yuke, et al.
Pubblicazione: (2023)

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
di: Wang, Yujing, et al.
Pubblicazione: (2024)

Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks
di: Noorbakhsh, Sayedeh Leila, et al.
Pubblicazione: (2024)

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
di: Wang, Xunguang, et al.
Pubblicazione: (2024)

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
di: Lorenz, Tobias, et al.
Pubblicazione: (2024)

Exact Certification of (Graph) Neural Networks Against Label Poisoning
di: Sabanayagam, Mahalakshmi, et al.
Pubblicazione: (2024)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
di: Yang, Yuxin, et al.
Pubblicazione: (2024)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
di: Zhou, Shuai, et al.
Pubblicazione: (2024)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
di: Chen, Yulin, et al.
Pubblicazione: (2025)

Invariant Aggregator for Defending against Federated Backdoor Attacks
di: Wang, Xiaoyang, et al.
Pubblicazione: (2022)

Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
di: De Gaspari, Fabio, et al.
Pubblicazione: (2024)

CyberAlly: Leveraging LLMs and Knowledge Graphs to Empower Cyber Defenders
di: Kim, Minjune, et al.
Pubblicazione: (2025)

Defending against Indirect Prompt Injection by Instruction Detection
di: Wen, Tongyu, et al.
Pubblicazione: (2025)

Defending against Data Poisoning Attacks in Federated Learning via User Elimination
di: Galanis, Nick
Pubblicazione: (2024)

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

Safeguarding Graph Neural Networks against Topology Inference Attacks
di: Fu, Jie, et al.
Pubblicazione: (2025)

Hijacking Attacks against Neural Networks by Analyzing Training Data
di: Ge, Yunjie, et al.
Pubblicazione: (2024)

RADAR: Defending RAG Dynamically against Retrieval Corruption
di: Chen, Ziyuan, et al.
Pubblicazione: (2026)

Backdoor Attacks on Discrete Graph Diffusion Models
di: Wang, Jiawen, et al.
Pubblicazione: (2025)

VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data
di: Du, Xuefeng, et al.
Pubblicazione: (2024)

MEA-Defender: A Robust Watermark against Model Extraction Attack
di: Lv, Peizhuo, et al.
Pubblicazione: (2024)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
di: Guo, Ji, et al.
Pubblicazione: (2024)

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
di: Yu, Zhe, et al.
Pubblicazione: (2026)

GCON: Differentially Private Graph Convolutional Network via Objective Perturbation
di: Wei, Jianxin, et al.
Pubblicazione: (2024)

PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification
di: Gong, Guangyu, et al.
Pubblicazione: (2026)

BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks
di: Lee, Hanyong, et al.
Pubblicazione: (2025)

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
di: Cheng, Xueqi, et al.
Pubblicazione: (2025)

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

"What is the Problem Space?" Defining Host-space Adversarial Perturbations against Network Intrusion Detection Systems
di: Verkerken, Miel, et al.
Pubblicazione: (2026)

ShieldMMU: Detecting and Defending against Controlled-Channel Attacks in Shielding Memory System
di: Liu, Gang, et al.
Pubblicazione: (2025)

A Defender-Attacker-Defender Model for Optimizing the Resilience of Hospital Networks to Cyberattacks
di: Helfrich, Stephan, et al.
Pubblicazione: (2026)

From Defender to Devil? Unintended Risk Interactions Induced by LLM Defenses
di: Meng, Xiangtao, et al.
Pubblicazione: (2025)