ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
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.
Code (1)
Tasks
Backdoor AttackMachine UnlearningSimilar Papers 제목 키워드 기반
Defending against Backdoor Attacks in Natural Language Generation
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+1Defending Against Backdoor Attacks in Natural Language Generation
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+1SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
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 RecognitionChar-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs
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 TransferUIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
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