Image de couverture de livre

Mitigating Backdoor Attacks using Activation-Guided Model Editing

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hsieh, Felix, Nguyen, Huy H., MaungMaung, AprilPyone, Usynin, Dmitrii, Echizen, Isao
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
par: MaungMaung, AprilPyone, et autres
Publié: (2024)

Beyond Standard Benchmarks: A Systematic Audit of Vision-Language Model's Robustness to Natural Semantic Variation Across Diverse Tasks
par: Chengyu, Jia, et autres
Publié: (2026)

EditSleuth: A Dataset of Grounded Reasoning Chains for Image-Edit Forensics
par: Nguyen, Van-Loc, et autres
Publié: (2026)

SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
par: Wang, Hongbo, et autres
Publié: (2025)

Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance
par: Ouyang, Tinghui, et autres
Publié: (2024)

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

Tell-Tale Watermarks for Explanatory Reasoning in Synthetic Media Forensics
par: Chang, Ching-Chun, et autres
Publié: (2025)

FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attacks
par: Nguyen, Duong H., et autres
Publié: (2024)

Agentic Copyright Watermarking against Adversarial Evidence Forgery with Purification-Agnostic Curriculum Proxy Learning
par: Bao, Erjin, et autres
Publié: (2024)

GreedyPixel: Fine-Grained Black-Box Adversarial Attack Via Greedy Algorithm
par: Wang, Hanrui, et autres
Publié: (2025)

DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
par: Wang, Hanrui, et autres
Publié: (2025)

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

Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models
par: Belfiore, Asia, et autres
Publié: (2025)

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

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
par: Nakka, Krishna Kanth, et autres
Publié: (2025)

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

Backdoor Attack with Mode Mixture Latent Modification
par: Zhang, Hongwei, et autres
Publié: (2024)

Cyber Vaccine for Deepfake Immunity
par: Chang, Ching-Chun, et autres
Publié: (2023)

BadDet+: Robust Backdoor Attacks for Object Detection
par: Dunnett, Kealan, et autres
Publié: (2026)

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

Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
par: Li, Qian, et autres
Publié: (2026)

SATBA: An Invisible Backdoor Attack Based On Spatial Attention
par: Zhou, Huasong, et autres
Publié: (2023)

HoneypotNet: Backdoor Attacks Against Model Extraction
par: Wang, Yixu, et autres
Publié: (2025)

Universal Backdoor Attacks
par: Schneider, Benjamin, et autres
Publié: (2023)

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

Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
par: Dunnett, Kealan, et autres
Publié: (2026)

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

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

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
par: Zhong, Zhiyuan, et autres
Publié: (2025)

Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models
par: Zhang, Zongmin, et autres
Publié: (2025)

ConSeg: Contextual Backdoor Attack Against Semantic Segmentation
par: Abbasi, Bilal Hussain, et autres
Publié: (2025)

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

Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning
par: Ali, Hassan, et autres
Publié: (2024)

Data Free Backdoor Attacks
par: Cao, Bochuan, et autres
Publié: (2024)

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

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

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

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
par: Zhang, Lei, et autres
Publié: (2025)

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

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