Prototype Guided Backdoor Defense
Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifications. Various triggers have been used, including semantic triggers that are easily realizable without requiring the attacker to manipulate the image. The emergence of generative AI has eased the generation of varied poisoned samples. Robustness across types of triggers is crucial to effective defense. We propose Prototype Guided Backdoor Defense (PGBD), a robust post-hoc defense that scales across different trigger types, including previously unsolved semantic triggers. PGBD exploits displacements in the geometric spaces of activations to penalize movements toward the trigger. This is done using a novel sanitization loss of a post-hoc fine-tuning step. The geometric approach scales easily to all types of attacks. PGBD achieves better performance across all settings. We also present the first defense against a new semantic attack on celebrity face images. Project page: \hyperlink{https://venkatadithya9.github.io/pgbd.github.io/}{this https URL}.
Code (0)
등록된 구현이 없습니다.
Tasks
backdoor defenseSimilar Papers 제목 키워드 기반
A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning
Defending backdoor attacks in Federated Learning (FL) under heterogeneous client data distributions encounters limitations balancing effectiveness and privacy-preserving, while most existing methods highly rely on the as…
Federated LearningZero-Shot LearningCLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computa…
backdoor defenseBadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be eas…
Backdoor AttackContrastive LearningRemoving the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
Current backdoor defenses assume that neutralizing a known trigger removes the backdoor. We show this trigger-centric view is incomplete: \emph{alternative triggers}, patterns perceptually distinct from training triggers…
Backdoor Defense via Adaptively Splitting Poisoned Dataset
Backdoor defenses have been studied to alleviate the threat of deep neural networks (DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt some external training data from an untrusted thir…
backdoor defense