Cover Image

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ding, Ruyi, Xu, Tianhong, Shen, Xinyi, Ding, Aidong Adam, Fei, Yunsi
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EXAM: Exploiting Exclusive System-Level Cache in Apple M-Series SoCs for Enhanced Cache Occupancy Attacks
by: Xu, Tianhong, et al.
Published: (2025)

Graph in the Vault: Protecting Edge GNN Inference with Trusted Execution Environment
by: Ding, Ruyi, et al.
Published: (2025)

MACPruning: Dynamic Operation Pruning to Mitigate Side-Channel DNN Model Extraction
by: Ding, Ruyi, et al.
Published: (2025)

Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
by: Ding, Ruyi, et al.
Published: (2024)

Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
by: Fei, Zekun, et al.
Published: (2026)

USBSnoop -- Revealing Device Activities via USB Congestions
by: Ranney, Davis, et al.
Published: (2025)

Exploiting Inaccurate Branch History in Side-Channel Attacks
by: Zhu, Yuhui, et al.
Published: (2025)

The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise
by: Lupinacci, Matteo, et al.
Published: (2025)

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing
by: Zhou, Yifan, et al.
Published: (2025)

SleepWalk: Exploiting Context Switching and Residual Power for Physical Side-Channel Attacks
by: Sanjaya, Sahan, et al.
Published: (2025)

GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs
by: Wu, Lichao, et al.
Published: (2025)

MetaSeal: Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks
by: Zhou, Tong, et al.
Published: (2025)

Exploiting HDMI and USB Ports for GPU Side-Channel Insights
by: Arefin, Sayed Erfan, et al.
Published: (2024)

Click Without Compromise: Online Advertising Measurement via Per User Differential Privacy
by: Xiao, Yingtai, et al.
Published: (2024)

Side-Channel Attacks on Open vSwitch
by: Kim, Daewoo, et al.
Published: (2026)

On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel
by: Shukla, Shubhi, et al.
Published: (2022)

NetEcho: From Real-World Streaming Side-Channels to Full LLM Conversation Recovery
by: Zhang, Zheng, et al.
Published: (2025)

MoPE: A Mixture of Password Experts for Improving Password Guessing
by: Duan, Mingjian, et al.
Published: (2025)

A Hardware-Friendly Shuffling Countermeasure Against Side-Channel Attacks for Kyber
by: Xu, Dejun, et al.
Published: (2024)

Acoustic Side-Channel Attacks on a Computer Mouse
by: Conti, Mauro, et al.
Published: (2025)

THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX
by: Dizani, Farshad, et al.
Published: (2025)

Last-Level Cache Side-Channel Attacks Are Feasible in the Modern Public Cloud (Extended Version)
by: Zhao, Zirui Neil, et al.
Published: (2024)

SNPeek: Side-Channel Analysis for Privacy Applications on Confidential VMs
by: Zhang, Ruiyi, et al.
Published: (2025)

Adversarial Attack Based Countermeasures against Deep Learning Side-Channel Attacks
by: Gu, Ruizhe, et al.
Published: (2020)

Exploiting Timing Side-Channels in Quantum Circuits Simulation Via ML-Based Methods
by: Dong, Ben, et al.
Published: (2025)

DP-Dueling: Learning from Preference Feedback without Compromising User Privacy
by: Saha, Aadirupa, et al.
Published: (2024)

Acoustic Side Channel Attack on Keyboards Based on Typing Patterns
by: Taheritajar, Alireza, et al.
Published: (2024)

Lightweight Countermeasures Against Static Power Side-Channel Attacks
by: Bhandari, Jitendra, et al.
Published: (2024)

Machine Learning Power Side-Channel Attack on SNOW-V
by: Deepak, et al.
Published: (2025)

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy
by: Cui, Yu, et al.
Published: (2025)

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
by: Bai, Li, et al.
Published: (2025)

BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
by: Wang, Qingyue, et al.
Published: (2025)

Privacy Side Channels in Machine Learning Systems
by: Debenedetti, Edoardo, et al.
Published: (2023)

NVBleed: Covert and Side-Channel Attacks on NVIDIA Multi-GPU Interconnect
by: Zhang, Yicheng, et al.
Published: (2025)

Application-Specific Power Side-Channel Attacks and Countermeasures: A Survey
by: Sanjaya, Sahan, et al.
Published: (2025)

Protecting Cryptographic Libraries against Side-Channel and Code-Reuse Attacks
by: Tsoupidi, Rodothea Myrsini, et al.
Published: (2024)

Towards Strengthening Deep Learning-based Side Channel Attacks with Mixup
by: Luo, Zhimin, et al.
Published: (2021)

BadPatches: Routing-aware Backdoor Attacks on Vision Mixture of Experts
by: Chan, Cedric, et al.
Published: (2025)

Breaking ECDSA with Electromagnetic Side-Channel Attacks: Challenges and Practicality on Modern Smartphones
by: Oberhansl, Felix, et al.
Published: (2025)

Memory Under Siege: A Comprehensive Survey of Side-Channel Attacks on Memory
by: Hassan, MD Mahady, et al.
Published: (2025)