GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning
Within the realm of computer vision, self-supervised learning (SSL) pertains to training pre-trained image encoders utilizing a substantial quantity of unlabeled images. Pre-trained image encoders can serve as feature extractors, facilitating the construction of downstream classifiers for various tasks. However, the use of SSL has led to an increase in security research related to various backdoor attacks. Currently, the trigger patterns used in backdoor attacks on SSL are mostly visible or static (sample-agnostic), making backdoors less covert and significantly affecting the attack performance. In this work, we propose GhostEncoder, the first dynamic invisible backdoor attack on SSL. Unlike existing backdoor attacks on SSL, which use visible or static trigger patterns, GhostEncoder utilizes image steganography techniques to encode hidden information into benign images and generate backdoor samples. We then fine-tune the pre-trained image encoder on a manipulation dataset to inject the backdoor, enabling downstream classifiers built upon the backdoored encoder to inherit the backdoor behavior for target downstream tasks. We evaluate GhostEncoder on three downstream tasks and results demonstrate that GhostEncoder provides practical stealthiness on images and deceives the victim model with a high attack success rate without compromising its utility. Furthermore, GhostEncoder withstands state-of-the-art defenses, including STRIP, STRIP-Cl, and SSL-Cleanse.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor AttackImage SteganographySelf-Supervised LearningSimilar Papers 제목 키워드 기반
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clea…
Backdoor Attackbackdoor defenseVocal Bursts Valence PredictionRethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threate…
Backdoor AttackText ClassificationFTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning
Current backdoor attacks against federated learning (FL) strongly rely on universal triggers or semantic patterns, which can be easily detected and filtered by certain defense mechanisms such as norm clipping, comparing …
Backdoor AttackFederated LearningA Backdoor Attack Scheme with Invisible Triggers Based on Model Architecture Modification
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious sampl…
Backdoor AttackThe Art of Deception: Robust Backdoor Attack using Dynamic Stacking of Triggers
The area of Machine Learning as a Service (MLaaS) is experiencing increased implementation due to recent advancements in the AI (Artificial Intelligence) industry. However, this spike has prompted concerns regarding AI d…
Backdoor Attackspeech-recognitionSpeech Recognition