Image de couverture de livre

Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhu, Rui, Tang, Di, Tang, Siyuan, Wang, XiaoFeng, Tang, Haixu
Format:	Preprint
Publié:	2022
Sujets:	Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
par: Zhu, Rui, et autres
Publié: (2023)

LLM-Enhanced Software Patch Localization
par: Yu, Jinhong, et autres
Publié: (2024)

Event Trojan: Asynchronous Event-based Backdoor Attacks
par: Wang, Ruofei, et autres
Publié: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
par: Jin, Haibo, et autres
Publié: (2021)

Multi-Target Federated Backdoor Attack Based on Feature Aggregation
par: Hao, Lingguag, et autres
Publié: (2025)

Clues in Tweets: Twitter-Guided Discovery and Analysis of SMS Spam
par: Tang, Siyuan, et autres
Publié: (2022)

Query-Efficient Video Adversarial Attack with Stylized Logo
par: Tang, Duoxun, et autres
Publié: (2024)

Robust Anti-Backdoor Instruction Tuning in LVLMs
par: Xun, Yuan, et autres
Publié: (2025)

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

IndirectAD: Practical Data Poisoning Attacks against Recommender Systems for Item Promotion
par: Wang, Zihao, et autres
Publié: (2025)

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
par: Cheng, Siyuan, et autres
Publié: (2024)

Stealthy Peers: Understanding Security Risks of WebRTC-Based Peer-Assisted Video Streaming
par: Tang, Siyuan, et autres
Publié: (2022)

The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
par: Chen, Xiaoyi, et autres
Publié: (2023)

DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models
par: Sui, Yang, et autres
Publié: (2024)

Towards Physical World Backdoor Attacks against Skeleton Action Recognition
par: Zheng, Qichen, et autres
Publié: (2024)

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
par: Cheng, Siyuan, et autres
Publié: (2024)

BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
par: Yang, Ziqing, et autres
Publié: (2026)

Leaky Cauldron on the Dark Land: Understanding Memory Side-Channel Hazards in SGX
par: Wang, Wenhao, et autres
Publié: (2017)

IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
par: Wang, Jiayao, et autres
Publié: (2025)

Backdooring CLIP through Concept Confusion
par: Hu, Lijie, et autres
Publié: (2025)

A Survey of Trojan Attacks and Defenses to Deep Neural Networks
par: Jin, Lingxin, et autres
Publié: (2024)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
par: Wei, Shaokui, et autres
Publié: (2024)

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

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

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
par: Li, Ziqiang, et autres
Publié: (2023)

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
par: Yu, Yi, et autres
Publié: (2024)

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
par: Liu, Kuanrong, et autres
Publié: (2024)

PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
par: Liu, Dazhuang, et autres
Publié: (2026)

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
par: Zheng, Mengxin, et autres
Publié: (2023)

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

BlindU: Blind Machine Unlearning without Revealing Erasing Data
par: Wang, Weiqi, et autres
Publié: (2026)

Backdoor Cleaning without External Guidance in MLLM Fine-tuning
par: Rong, Xuankun, et autres
Publié: (2025)

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

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

Evil from Within: Machine Learning Backdoors through Hardware Trojans
par: Warnecke, Alexander, et autres
Publié: (2023)

Clean-image Backdoor Attacks
par: Rong, Dazhong, et autres
Publié: (2024)

Backdoor Directions in Vision Transformers
par: Karayalcin, Sengim, et autres
Publié: (2026)

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
par: Li, Boheng, et autres
Publié: (2024)

CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World
par: Zhao, Shuxin, et autres
Publié: (2025)

Test-Time Attention Purification for Backdoored Large Vision Language Models
par: Zhang, Zhifang, et autres
Publié: (2026)