Image de couverture de livre

LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Beichen, Guo, Yuanfang, Peng, Heqi, Li, Yangxi, Wang, Yunhong
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
par: Peng, Heqi, et autres
Publié: (2024)

Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
par: Huang, Binxiao, et autres
Publié: (2024)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
par: Li, Zida, et autres
Publié: (2026)

REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
par: Guo, Chongye, et autres
Publié: (2025)

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
par: Iftee, Md Akil Raihan, et autres
Publié: (2025)

A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
par: Li, Ziqiang, et autres
Publié: (2023)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
par: He, Yuhao, et autres
Publié: (2024)

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
par: Jang, Sangwon, et autres
Publié: (2025)

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget
par: Yang, Yi, et autres
Publié: (2026)

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
par: Sun, Mengyuan, et autres
Publié: (2025)

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
par: Zhu, Mingyan, et autres
Publié: (2023)

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
par: Hong, Sanghyun, et autres
Publié: (2024)

Delta-Influence: Unlearning Poisons via Influence Functions
par: Li, Wenjie, et autres
Publié: (2024)

VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference
par: Qi, Minfeng, et autres
Publié: (2026)

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
par: Wang, Hao, et autres
Publié: (2024)

IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields
par: Jiang, Wenxiang, et autres
Publié: (2024)

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
par: Nguyen, Quang H., et autres
Publié: (2024)

PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning
par: Hussein, Noor, et autres
Publié: (2024)

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
par: Yu, Yi, et autres
Publié: (2024)

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
par: Struppek, Lukas, et autres
Publié: (2023)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
par: Abad, Gorka, et autres
Publié: (2026)

Deepfake Detection via Knowledge Injection
par: Li, Tonghui, et autres
Publié: (2025)

Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
par: Wang, Ruotong, et autres
Publié: (2023)

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation
par: Yu, Yi, et autres
Publié: (2025)

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
par: Jia, Yuqi, et autres
Publié: (2024)

Machine Learning Security against Data Poisoning: Are We There Yet?
par: Cinà, Antonio Emanuele, et autres
Publié: (2022)

Energy-Latency Attacks via Sponge Poisoning
par: Cinà, Antonio Emanuele, et autres
Publié: (2022)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
par: Lin, Miao, et autres
Publié: (2026)

One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks
par: Guo, Ji, et autres
Publié: (2024)

TPatch: A Triggered Physical Adversarial Patch
par: Zhu, Wenjun, et autres
Publié: (2023)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
par: Chen, Hao, et autres
Publié: (2025)

Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
par: Gong, Xueluan, et autres
Publié: (2024)

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
par: Zhuang, Haomin, et autres
Publié: (2023)

A4O: All Trigger for One sample
par: Vu, Duc Anh, et autres
Publié: (2025)

PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction
par: Wadekar, Prajas, et autres
Publié: (2026)

Backdoor Attack with Sparse and Invisible Trigger
par: Gao, Yinghua, et autres
Publié: (2023)

Cover-separable Fixed Neural Network Steganography via Deep Generative Models
par: Li, Guobiao, et autres
Publié: (2024)

VidLeaks: Membership Inference Attacks Against Text-to-Video Models
par: Wang, Li, et autres
Publié: (2026)

DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
par: Zhang, Yitong, et autres
Publié: (2025)

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
par: Wang, Xianlong, et autres
Publié: (2024)