Copertina

BadPatches: Routing-aware Backdoor Attacks on Vision Mixture of Experts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chan, Cedric, Lintelo, Jona te, Picek, Stjepan
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

Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing
di: Lintelo, Jona te, et al.
Pubblicazione: (2026)

The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks
di: Lintelo, Jona te, et al.
Pubblicazione: (2024)

MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
di: Lintelo, Jona te, et al.
Pubblicazione: (2026)

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

GoodVibe: Security-by-Vibe for LLM-Based Code Generation
di: Thang, Maximilian, et al.
Pubblicazione: (2026)

Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers
di: Abad, Gorka, et al.
Pubblicazione: (2024)

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

CatBack: Universal Backdoor Attacks on Tabular Data via Categorical Encoding
di: Tajalli, Behrad, et al.
Pubblicazione: (2025)

Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras
di: Riaño, Roberto, et al.
Pubblicazione: (2024)

EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody
di: Schoof, Coen, et al.
Pubblicazione: (2024)

Let's Focus: Focused Backdoor Attack against Federated Transfer Learning
di: Arazzi, Marco, et al.
Pubblicazione: (2024)

Time-Distributed Backdoor Attacks on Federated Spiking Learning
di: Abad, Gorka, et al.
Pubblicazione: (2024)

Backdoor Directions in Vision Transformers
di: Karayalcin, Sengim, et al.
Pubblicazione: (2026)

Towards Backdoor Stealthiness in Model Parameter Space
di: Xu, Xiaoyun, et al.
Pubblicazione: (2025)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
di: Abad, Gorka, et al.
Pubblicazione: (2026)

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

Backdoor Attacks on Transformers for Tabular Data: An Empirical Study
di: Pleiter, Bart, et al.
Pubblicazione: (2023)

More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks
di: Xu, Jing, et al.
Pubblicazione: (2022)

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

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
di: Zhao, Xin, et al.
Pubblicazione: (2025)

BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
di: Xu, Xiaoyun, et al.
Pubblicazione: (2024)

NoMod: A Non-modular Attack on Module Learning With Errors
di: Bassotto, Cristian, et al.
Pubblicazione: (2025)

NeuroStrike: Neuron-Level Attacks on Aligned LLMs
di: Wu, Lichao, et al.
Pubblicazione: (2025)

A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
di: Xu, Zihao, et al.
Pubblicazione: (2024)

Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
di: Karayalçin, Sengim, et al.
Pubblicazione: (2025)

$$\mathbf{L^2\cdot M = C^2}$$ Large Language Models are Covert Channels
di: Gaure, Simen, et al.
Pubblicazione: (2024)

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

BadMerging: Backdoor Attacks Against Model Merging
di: Zhang, Jinghuai, et al.
Pubblicazione: (2024)

BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting
di: Xiang, Kunlan, et al.
Pubblicazione: (2025)

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
di: Yuan, Zenghui, et al.
Pubblicazione: (2025)

BadViM: Backdoor Attack against Vision Mamba
di: Wu, Yinghao, et al.
Pubblicazione: (2025)

Membership Privacy Evaluation in Deep Spiking Neural Networks
di: Li, Jiaxin, et al.
Pubblicazione: (2024)

BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models
di: Wang, Jiayao, et al.
Pubblicazione: (2026)

Label Inference Attacks against Node-level Vertical Federated GNNs
di: Arazzi, Marco, et al.
Pubblicazione: (2023)

You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation
di: Arazzi, Marco, et al.
Pubblicazione: (2026)

SoK: The Last Line of Defense: On Backdoor Defense Evaluation
di: Abad, Gorka, et al.
Pubblicazione: (2025)

BadDet+: Robust Backdoor Attacks for Object Detection
di: Dunnett, Kealan, et al.
Pubblicazione: (2026)

BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
di: Tie, Guiyao, et al.
Pubblicazione: (2026)

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
di: Wang, Zihan, et al.
Pubblicazione: (2026)

PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
di: Liu, Dazhuang, et al.
Pubblicazione: (2026)