Imagen de Portada

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qin, Shixi, Yang, Zhiyong, Bao, Shilong, Wang, Shi, Xu, Qianqian, Huang, Qingming
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
por: Chen, Tianxin, et al.
Publicado: (2026)

Heterogeneous Graph Backdoor Attack
por: Chen, Jiawei, et al.
Publicado: (2025)

Backdoor Attacks against Image-to-Image Networks
por: Jiang, Wenbo, et al.
Publicado: (2024)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
por: Li, Yige, et al.
Publicado: (2025)

BridgeShield: Enhancing Security for Cross-chain Bridge Applications via Heterogeneous Graph Mining
por: Lin, Dan, et al.
Publicado: (2025)

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
por: Zhang, Rui, et al.
Publicado: (2025)

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
por: Ma, Oubo, et al.
Publicado: (2025)

Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
por: Song, Baogang, et al.
Publicado: (2025)

SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning
por: Xu, Weida, et al.
Publicado: (2024)

Concept-Guided Backdoor Attack on Vision Language Models
por: Shen, Haoyu, et al.
Publicado: (2025)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
por: Truong, Vu Tuan, et al.
Publicado: (2026)

Invisible Textual Backdoor Attacks based on Dual-Trigger
por: Hou, Yang, et al.
Publicado: (2024)

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
por: Qiu, Huming, et al.
Publicado: (2023)

Backdoor Attack with Invisible Triggers Based on Model Architecture Modification
por: Ma, Yuan, et al.
Publicado: (2024)

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

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

ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
por: Yang, Feiyu, et al.
Publicado: (2025)

Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping
por: Wang, Lei, et al.
Publicado: (2025)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
por: Feng, Yunhao, et al.
Publicado: (2026)

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
por: Ge, Huaizhi, et al.
Publicado: (2024)

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
por: Zheng, Jingyi, et al.
Publicado: (2024)

DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
por: Popovic, Dorde, et al.
Publicado: (2025)

Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models
por: Chen, Linzhi, et al.
Publicado: (2025)

Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
por: Li, Zi, et al.
Publicado: (2026)

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
por: Lin, Chenhao, et al.
Publicado: (2025)

Clean-Label Physical Backdoor Attacks with Data Distillation
por: Dao, Thinh, et al.
Publicado: (2024)

Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
por: Ning, Liangbo, et al.
Publicado: (2025)

Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
por: Zhao, Jingke, et al.
Publicado: (2024)

Beyond Immediate Activation: Temporally Decoupled Backdoor Attacks on Time Series Forecasting
por: Liu, Zhixin, et al.
Publicado: (2026)

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models
por: Ding, Zikang, et al.
Publicado: (2026)

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
por: Yang, He, et al.
Publicado: (2026)

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models
por: Li, Yuetai, et al.
Publicado: (2024)

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
por: Jin, Haotian, et al.
Publicado: (2025)

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

SFIBA: Spatial-based Full-target Invisible Backdoor Attacks
por: Yin, Yangxu, et al.
Publicado: (2025)

Does Few-shot Learning Suffer from Backdoor Attacks?
por: Liu, Xinwei, et al.
Publicado: (2023)

Stealthy Backdoor Attack to Real-world Models in Android Apps
por: Wei, Jiali, et al.
Publicado: (2025)

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
por: Li, Xi, et al.
Publicado: (2024)

Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs
por: Cui, Jing, et al.
Publicado: (2025)

Injecting Bias into Text Classification Models using Backdoor Attacks
por: Yavuz, A. Dilara, et al.
Publicado: (2024)