Copertina

Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Xincheng, Ranbaduge, Thilina, Wang, Qing, Rakotoarivelo, Thierry, Smith, David
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Privacy risk in GeoData: A survey
di: Lorestani, Mahrokh Abdollahi, et al.
Pubblicazione: (2024)

FERRET: Private Deep Learning Faster And Better Than DPSGD
di: Zagardo, David
Pubblicazione: (2025)

Privacy at a Price: Exploring its Dual Impact on AI Fairness
di: Yang, Mengmeng, et al.
Pubblicazione: (2024)

Private Knowledge Sharing in Distributed Learning: A Survey
di: Supeksala, Yasas, et al.
Pubblicazione: (2024)

Weights Shuffling for Improving DPSGD in Transformer-based Models
di: Yang, Jungang, et al.
Pubblicazione: (2024)

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction
di: Wu, Shuchi, et al.
Pubblicazione: (2023)

PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites
di: Kim, Jaehan, et al.
Pubblicazione: (2025)

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
di: Sha, Haichao, et al.
Pubblicazione: (2024)

Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing
di: Wahréus, Johan, et al.
Pubblicazione: (2025)

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
di: Yang, Junxiao, et al.
Pubblicazione: (2025)

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
di: Wang, Wenshuo, et al.
Pubblicazione: (2025)

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness
di: Hase, Ryo, et al.
Pubblicazione: (2024)

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
di: Wang, Cheng-Long, et al.
Pubblicazione: (2025)

Enhancing Reliability in LLM-Based Secure Code Generation
di: Kharma, Mohammed F., et al.
Pubblicazione: (2026)

Privacy Technologies for Financial Intelligence
di: Li, Yang, et al.
Pubblicazione: (2024)

Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data
di: Gokcen, Alpaslan, et al.
Pubblicazione: (2025)

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
di: Liu, Zhenyu, et al.
Pubblicazione: (2024)

Feature Selection via GANs (GANFS): Enhancing Machine Learning Models for DDoS Mitigation
di: Patel, Harsh
Pubblicazione: (2025)

DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
di: Wu, Huiwen, et al.
Pubblicazione: (2024)

Enhancing Vulnerability Reports with Automated and Augmented Description Summarization
di: Althebeiti, Hattan, et al.
Pubblicazione: (2025)

Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks
di: Shi, Haonan, et al.
Pubblicazione: (2024)

Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems
di: Wang, Luyao
Pubblicazione: (2026)

Learning to Watermark LLM-generated Text via Reinforcement Learning
di: Xu, Xiaojun, et al.
Pubblicazione: (2024)

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
di: Gao, Junqi, et al.
Pubblicazione: (2024)

Seed Hijacking of LLM Sampling and Quantum Random Number Defense
di: You, Ziyang, et al.
Pubblicazione: (2026)

Enhancing Cloud Network Resilience via a Robust LLM-Empowered Multi-Agent Reinforcement Learning Framework
di: Peng, Yixiao, et al.
Pubblicazione: (2026)

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
di: Yichao, Wu, et al.
Pubblicazione: (2025)

TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation
di: Cui, Tianyu, et al.
Pubblicazione: (2025)

Robust and Reliable Early-Stage Website Fingerprinting Attacks via Spatial-Temporal Distribution Analysis
di: Deng, Xinhao, et al.
Pubblicazione: (2024)

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
di: Kirci, Onur Alp, et al.
Pubblicazione: (2025)

Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial Attacks
di: Bokobza, Roey, et al.
Pubblicazione: (2024)

Privacy-Preserving Federated Learning via Homomorphic Adversarial Networks
di: Dong, Wenhan, et al.
Pubblicazione: (2024)

Detecting Cybersecurity Threats by Integrating Explainable AI with SHAP Interpretability and Strategic Data Sampling
di: Srisumrith, Norrakith, et al.
Pubblicazione: (2026)

LoRID: Low-Rank Iterative Diffusion for Adversarial Purification
di: Zollicoffer, Geigh, et al.
Pubblicazione: (2024)

Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samples
di: Stein, Kyle, et al.
Pubblicazione: (2024)

Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning
di: Dou, Xuhui, et al.
Pubblicazione: (2026)

FedCAP: Robust Federated Learning via Customized Aggregation and Personalization
di: Li, Youpeng, et al.
Pubblicazione: (2024)

CLASP: Training-Free LLM-Assisted Source Code Watermarking via Semantic-Preserving Transformations
di: Xu, Rui, et al.
Pubblicazione: (2025)

Backdoor Graph Condensation
di: Wu, Jiahao, et al.
Pubblicazione: (2024)

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data
di: Zhou, Andy, et al.
Pubblicazione: (2024)