Copertina

BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Shanmin, Zhao, Dongdong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
di: Zhu, Mingyan, et al.
Pubblicazione: (2023)

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
di: Chen, Yukun, et al.
Pubblicazione: (2025)

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
di: Jindal, Akshit, et al.
Pubblicazione: (2026)

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
di: Li, Boheng, et al.
Pubblicazione: (2025)

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness
di: Jang, Suhyeok, et al.
Pubblicazione: (2024)

Towards Personalized Federated Learning via Comprehensive Knowledge Distillation
di: Wang, Pengju, et al.
Pubblicazione: (2024)

Architectural Neural Backdoors from First Principles
di: Langford, Harry, et al.
Pubblicazione: (2024)

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
di: Singh, Naman Deep, et al.
Pubblicazione: (2024)

Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking
di: Qian, Shengsheng, et al.
Pubblicazione: (2023)

Backdoor Attack with Sparse and Invisible Trigger
di: Gao, Yinghua, et al.
Pubblicazione: (2023)

Backdoor Attacks on Deep Learning Face Detection
di: Roux, Quentin Le, et al.
Pubblicazione: (2025)

Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
di: Qiao, Ting, et al.
Pubblicazione: (2025)

When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
di: Hong, Ziming, et al.
Pubblicazione: (2025)

FedDefender: Backdoor Attack Defense in Federated Learning
di: Gill, Waris, et al.
Pubblicazione: (2023)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
di: Chen, Yukun, et al.
Pubblicazione: (2025)

FLARE: Toward Universal Dataset Purification against Backdoor Attacks
di: Hou, Linshan, et al.
Pubblicazione: (2024)

Backdooring Outlier Detection Methods: A Novel Attack Approach
di: Taghavi, ZeinabSadat, et al.
Pubblicazione: (2024)

PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
di: Wei, Cheng, et al.
Pubblicazione: (2024)

SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
di: Roux, Quentin Le, et al.
Pubblicazione: (2025)

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning
di: Liu, Tao, et al.
Pubblicazione: (2024)

Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations
di: Pang, Lu, et al.
Pubblicazione: (2024)

Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
di: Zhu, Rui, et al.
Pubblicazione: (2022)

Non-Cooperative Backdoor Attacks in Federated Learning: A New Threat Landscape
di: Nguyen, Tuan, et al.
Pubblicazione: (2024)

Personalized Federated Learning via Backbone Self-Distillation
di: Wang, Pengju, et al.
Pubblicazione: (2024)

Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks
di: Ahlers, Enrico, et al.
Pubblicazione: (2026)

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
di: Yang, Wenhan, et al.
Pubblicazione: (2023)

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
di: Stein, Kyle, et al.
Pubblicazione: (2024)

NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise
di: Miah, Abdullah Arafat, et al.
Pubblicazione: (2024)

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
di: Liu, Kuanrong, et al.
Pubblicazione: (2024)

Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation
di: Liu, Bochao, et al.
Pubblicazione: (2024)

Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
di: Raj, Ankita, et al.
Pubblicazione: (2025)

INK: Inheritable Natural Backdoor Attack Against Model Distillation
di: Liu, Xiaolei, et al.
Pubblicazione: (2023)

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention
di: Abdalla, Amro, et al.
Pubblicazione: (2025)

Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning
di: Wang, Chenan, et al.
Pubblicazione: (2024)

PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning
di: Xu, Yukai, et al.
Pubblicazione: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
di: Jin, Haibo, et al.
Pubblicazione: (2021)

Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning
di: Herath, Kavindu, et al.
Pubblicazione: (2026)

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
di: Zhao, Chengshuai, et al.
Pubblicazione: (2026)

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
di: Zhuang, Haomin, et al.
Pubblicazione: (2023)

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
di: Zhao, Shuai, et al.
Pubblicazione: (2024)