One Pixel is All I Need
원문 초록
Vision Transformers (ViTs) have achieved record-breaking performance in various visual tasks. However, concerns about their robustness against backdoor attacks have grown. Backdoor attacks involve associating a specific trigger with a target label, causing the model to predict the attacker-specified label when the trigger is present, while correctly identifying clean images.We found that ViTs exhibit higher attack success rates for quasi-triggers(patterns different from but similar to the original training triggers)compared to CNNs. Moreover, some backdoor features in clean samples can suppress the original trigger, making quasi-triggers more effective.To better understand and exploit these vulnerabilities, we developed a tool called the Perturbation Sensitivity Distribution Map (PSDM). PSDM computes and sums gradients over many inputs to show how sensitive the model is to small changes in the input. In ViTs, PSDM reveals a patch-like pattern where central pixels are more sensitive than edges. We use PSDM to guide the creation of quasi-triggers.Based on these findings, we designed "WorstVIT," a simple yet effective data poisoning backdoor for ViT models. This attack requires an extremely low poisoning rate, trains for just one epoch, and modifies a single pixel to successfully attack all validation images.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA
Is Diversity All You Need for Scalable Robotic Manipulation?
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
These are Not All the Features You are Looking For: A Fundamental Bottleneck In Supervised Pretraining
토론
이 논문과 연결된 포럼 글이 아직 없습니다.