Cover Image

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Blagoev, Nikolay, Ersoy, Oğuzhan, Chen, Lydia Yiyu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

F-TIS: Harnessing Diverse Models in Collaborative GRPO
by: Blagoev, Nikolay, et al.
Published: (2026)

All is Not Lost: LLM Recovery without Checkpoints
by: Blagoev, Nikolay, et al.
Published: (2025)

SkipPipe: Partial and Reordered Pipelining Framework for Training LLMs in Heterogeneous Networks
by: Blagoev, Nikolay, et al.
Published: (2025)

Backdoor Attacks on Decentralised Post-Training
by: Ersoy, Oğuzhan, et al.
Published: (2026)

NoLoCo: No-all-reduce Low Communication Training Method for Large Models
by: Kolehmainen, Jari, et al.
Published: (2025)

Go With The Flow: Churn-Tolerant Decentralized Training of Large Language Models
by: Blagoev, Nikolay, et al.
Published: (2025)

Training-Free Dynamic Upcycling of Expert Language Models
by: Fanì, Eros, et al.
Published: (2026)

Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
by: Abad, Gorka, et al.
Published: (2023)

HDEE: Heterogeneous Domain Expert Ensemble
by: Ersoy, Oğuzhan, et al.
Published: (2025)

Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
by: Wang, Hanxuan, et al.
Published: (2025)

LinkThief: Combining Generalized Structure Knowledge with Node Similarity for Link Stealing Attack against GNN
by: Zhang, Yuxing, et al.
Published: (2024)

LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
by: Lai, Yao, et al.
Published: (2026)

CAtCh: Cognitive Assessment through Cookie Thief
by: Colonel, Joseph T, et al.
Published: (2025)

FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning
by: Zhang, Xiangyu, et al.
Published: (2025)

Long-term Fairness in Ride-Hailing Platform
by: Kang, Yufan, et al.
Published: (2024)

Robustness of Decentralised Learning to Nodes and Data Disruption
by: Palmieri, Luigi, et al.
Published: (2024)

How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
by: Tian, Minghao, et al.
Published: (2026)

Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks
by: Niu, Peizhi, et al.
Published: (2024)

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
by: Yari, Amir Hossein, et al.
Published: (2026)

Decentralised Traffic Incident Detection via Network Lasso
by: Zhu, Qiyuan, et al.
Published: (2024)

Data Reconstruction Attacks and Defenses: A Systematic Evaluation
by: Liu, Sheng, et al.
Published: (2024)

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
by: Chen, Xiwen, et al.
Published: (2025)

Noise Masking Attacks and Defenses for Pretrained Speech Models
by: Jagielski, Matthew, et al.
Published: (2024)

Optimal Defenses Against Gradient Reconstruction Attacks
by: Chen, Yuxiao, et al.
Published: (2024)

An Asynchronous Decentralised Optimisation Algorithm for Nonconvex Problems
by: Mafakheri, Behnam, et al.
Published: (2025)

Frailty-Aware Transformer for Recurrent Survival Modeling of Driver Retention in Ride-Hailing Platforms
by: Xu, Shuoyan, et al.
Published: (2025)

Verde: Verification via Refereed Delegation for Machine Learning Programs
by: Arun, Arasu, et al.
Published: (2025)

Disparate Privacy Vulnerability: Targeted Attribute Inference Attacks and Defenses
by: Kabir, Ehsanul, et al.
Published: (2025)

AlignTree: Efficient Defense Against LLM Jailbreak Attacks
by: Goren, Gil, et al.
Published: (2025)

Attack and Defense of Deep Learning Models in the Field of Web Attack Detection
by: Shi, Lijia, et al.
Published: (2024)

Synthetic Tabular Data: Methods, Attacks and Defenses
by: Cormode, Graham, et al.
Published: (2025)

A Taxonomy of Attacks and Defenses in Split Learning
by: Shabbir, Aqsa, et al.
Published: (2025)

A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication
by: Wu, Weiming, et al.
Published: (2026)

D$^3$-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market
by: Chen, Taijie, et al.
Published: (2026)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
by: Zeng, Yifan, et al.
Published: (2024)

An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing
by: Yue, Xinlang, et al.
Published: (2024)

AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
by: Chen, Ying, et al.
Published: (2025)

Attacks and Defenses Against LLM Fingerprinting
by: Kurian, Kevin, et al.
Published: (2025)

Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
by: Li, Bin, et al.
Published: (2025)

On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses
by: Djilani, Mohamed, et al.
Published: (2025)