Imagen de Portada

GPU-Fuzz: Finding Memory Errors in Deep Learning Frameworks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Zihao, Lu, Hongyi, Guo, Yanan, Zhang, Zhenkai, Wang, Shuai, Zhang, Fengwei
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

Spin: An Efficient Secure Computation Framework with GPU Acceleration
por: Jiang, Wuxuan, et al.
Publicado: (2024)

ClawLess: A Security Model of AI Agents
por: Lu, Hongyi, et al.
Publicado: (2026)

NASimJax: GPU-Accelerated Policy Learning Framework for Penetration Testing
por: Simon, Raphael, et al.
Publicado: (2026)

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
por: Zhang, Yi, et al.
Publicado: (2025)

Unraveling the Key of Machine Learning-based Android Malware Detection
por: Liu, Jiahao, et al.
Publicado: (2024)

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
por: Dong, Yingkai, et al.
Publicado: (2024)

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
por: Chen, Wenyu, et al.
Publicado: (2026)

Challenges and Design Considerations for Finding CUDA Bugs Through GPU-Native Fuzzing
por: Li, Mingkai, et al.
Publicado: (2026)

SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
por: Partohaghighi, Mohammad, et al.
Publicado: (2026)

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
por: Qiu, Han, et al.
Publicado: (2020)

MOAT: Towards Safe BPF Kernel Extension
por: Lu, Hongyi, et al.
Publicado: (2023)

deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses
por: Androutsopoulos, Georgios, et al.
Publicado: (2025)

Real-PGDN: A Two-level Classification Method for Full-Process Recognition of Newly Registered Pornographic and Gambling Domain Names
por: Wang, Hao, et al.
Publicado: (2025)

FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework
por: Cai, Jinyu, et al.
Publicado: (2024)

Mitigating Error Amplification in Fast Adversarial Training
por: Zhao, Mengnan, et al.
Publicado: (2026)

TAPAS: Datasets for Learning the Learning with Errors Problem
por: Saxena, Eshika, et al.
Publicado: (2025)

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

Federated Learning for Cross-Domain Data Privacy: A Distributed Approach to Secure Collaboration
por: Zhang, Yiwei, et al.
Publicado: (2025)

Inference Privacy: Properties and Mechanisms
por: Tian, Fengwei, et al.
Publicado: (2024)

A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy
por: Li, Xiang, et al.
Publicado: (2025)

A New Federated Learning Framework Against Gradient Inversion Attacks
por: Guo, Pengxin, et al.
Publicado: (2024)

FedGA: Federated Learning with Gradient Alignment for Error Asymmetry Mitigation
por: Xiao, Chenguang, et al.
Publicado: (2024)

Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors
por: Zhang, Ruihan, et al.
Publicado: (2024)

Fuzzing the PHP Interpreter via Dataflow Fusion
por: Jiang, Yuancheng, et al.
Publicado: (2024)

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
por: Yuan, Shuai, et al.
Publicado: (2025)

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
por: Wu, Baoyuan, et al.
Publicado: (2024)

CNN architecture extraction on edge GPU
por: Horvath, Peter, et al.
Publicado: (2024)

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
por: Zhang, Mingxuan, et al.
Publicado: (2025)

Quantifying Policy Administration Cost in an Active Learning Framework
por: Zhang, Si, et al.
Publicado: (2023)

A Robust Adversary Detection-Deactivation Method for Metaverse-oriented Collaborative Deep Learning
por: Li, Pengfei, et al.
Publicado: (2023)

MUBox: A Critical Evaluation Framework of Deep Machine Unlearning
por: Li, Xiang, et al.
Publicado: (2025)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
por: Sheng, Leheng, et al.
Publicado: (2025)

Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors
por: Stevens, Samuel, et al.
Publicado: (2024)

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning
por: Zhang, Yiwei, et al.
Publicado: (2024)

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

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
por: Zhang, Xinwei, et al.
Publicado: (2023)

Transfer Learning for Security: Challenges and Future Directions
por: Li, Adrian Shuai, et al.
Publicado: (2024)

When AI Defeats Password Deception! A Deep Learning Framework to Distinguish Passwords and Honeywords
por: Dani, Jimmy, et al.
Publicado: (2024)

MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing
por: Ou, Shiwen, et al.
Publicado: (2025)

A Defensive Framework Against Adversarial Attacks on Machine Learning-Based Network Intrusion Detection Systems
por: Tafreshian, Benyamin, et al.
Publicado: (2025)