Cover Image

Architectural Neural Backdoors from First Principles

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Langford, Harry, Shumailov, Ilia, Zhao, Yiren, Mullins, Robert, Papernot, Nicolas
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Curse of Recursion: Training on Generated Data Makes Models Forget
by: Shumailov, Ilia, et al.
Published: (2023)

Locking Machine Learning Models into Hardware
by: Clifford, Eleanor, et al.
Published: (2024)

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
by: Küchler, Nicolas, et al.
Published: (2025)

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated
by: Foerster, Hanna, et al.
Published: (2025)

Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD
by: Thudi, Anvith, et al.
Published: (2023)

Beyond Slow Signs in High-fidelity Model Extraction
by: Foerster, Hanna, et al.
Published: (2024)

BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
by: Wang, Shanmin, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

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

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

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

ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
by: Clifford, Eleanor, et al.
Published: (2022)

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

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

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

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

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

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

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

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

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

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

Impact of Architectural Modifications on Deep Learning Adversarial Robustness
by: Juraev, Firuz, et al.
Published: (2024)

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

Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures
by: Dibbo, Sayanton V., et al.
Published: (2024)

Memory Backdoor Attacks on Neural Networks
by: Luzon, Eden, et al.
Published: (2024)

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
by: Foerster, Hanna, et al.
Published: (2026)

Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations
by: Oskouie, Haniyeh Ehsani, et al.
Published: (2022)

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
by: Shumailov, Ilia, et al.
Published: (2024)

Null Space Properties of Neural Networks with Applications to Image Steganography
by: Li, Xiang, et al.
Published: (2024)

Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses
by: Glukhov, David, et al.
Published: (2024)

LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks
by: Xu, Yongjie, et al.
Published: (2024)