paper-with-me

Papers

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning

2025-02-17 · Manaar Alam, Hithem Lamri, Michail Maniatakos

Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade detection by maintaining a low pre-deployment attack success rate (ASR) and restoring high ASR post-deployment via machine unlearning. Existing concealed backdoors are often constrained by requiring white-box or black-box access or auxiliary data, limiting their practicality when such access or data is unavailable. This paper introduces ReVeil, a concealed backdoor attack targeting the data collection phase of the DNN training pipeline, requiring no model access or auxiliary data. ReVeil maintains low pre-deployment ASR across four datasets and four trigger patterns, successfully evades three popular backdoor detection methods, and restores high ASR post-deployment through machine unlearning.

📄 PDF Abstract BibTeX arXiv:2502.11687

Code (1)

momalab/ReVeil 공식 구현 pytorch

Tasks

Backdoor AttackMachine Unlearning

Similar Papers 제목 키워드 기반

Defending against Backdoor Attacks in Natural Language Generation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunatel…

Backdoor AttackDialogue GenerationMachine TranslationText Generation+1

Defending Against Backdoor Attacks in Natural Language Generation

2021-06-03 · Xiaofei Sun, Xiaoya Li, Yuxian Meng, Xiang Ao 외

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately…

Backdoor AttackDialogue GenerationMachine TranslationText Generation+1

SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems

2025-07-02 · Quentin Le Roux, Yannick Teglia, Teddy Furon, Philippe Loubet-Moundi 외 arxiv

The widespread deployment of Deep Learning-based Face Recognition Systems raises many security concerns. While prior research has identified backdoor vulnerabilities on isolated components, Backdoor Attacks on real-world…

Face Recognition

Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs

2025-02-24 · Himanshu Beniwal, Sailesh Panda, Birudugadda Srivibhav, Mayank Singh

We explore \textbf{C}ross-lingual \textbf{B}ackdoor \textbf{AT}tacks (X-BAT) in multilingual Large Language Models (mLLMs), revealing how backdoors inserted in one language can automatically transfer to others through sh…

Cross-Lingual Transfer

UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models

2024-12-16 · CVPR 2025 1 · Yuning Han, Bingyin Zhao, Rui Chu, Feng Luo 외

Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarka…

Backdoor Attack