Using Interleaved Ensemble Unlearning to Keep Backdoors at Bay for Finetuning Vision Transformers
Vision Transformers (ViTs) have become popular in computer vision tasks. Backdoor attacks, which trigger undesirable behaviours in models during inference, threaten ViTs' performance, particularly in security-sensitive tasks. Although backdoor defences have been developed for Convolutional Neural Networks (CNNs), they are less effective for ViTs, and defences tailored to ViTs are scarce. To address this, we present Interleaved Ensemble Unlearning (IEU), a method for finetuning clean ViTs on backdoored datasets. In stage 1, a shallow ViT is finetuned to have high confidence on backdoored data and low confidence on clean data. In stage 2, the shallow ViT acts as a ``gate'' to block potentially poisoned data from the defended ViT. This data is added to an unlearn set and asynchronously unlearned via gradient ascent. We demonstrate IEU's effectiveness on three datasets against 11 state-of-the-art backdoor attacks and show its versatility by applying it to different model architectures.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the…
Continual PretrainingGet Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning
Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes …
Federated Learningimage-classificationImage ClassificationMachine UnlearningReVeil: 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, conceal…
Backdoor AttackMachine UnlearningTAPE: Tailored Posterior Difference for Auditing of Machine Unlearning
With the increasing prevalence of Web-based platforms handling vast amounts of user data, machine unlearning has emerged as a crucial mechanism to uphold users' right to be forgotten, enabling individuals to request the …
Machine UnlearningBackdoor Unlearning by Linear Task Decomposition
Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and targeted backdoor attacks. Mitigating such…