Search Results for author:
Found 4 papers, 2 papers with code
Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
In this paper, we explore the possibility of a less-cost defense from the perspective of model unlearning, that is, whether the model can be made to quickly \textbf{u}nlearn \textbf{b}ackdoor \textbf{t}hreats (UBT) by constructing a small set of poisoned samples.
VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
Nevertheless, the frozen visual encoder in autoregressive VLMs imposes constraints on the learning of conventional image triggers.
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
However, this paper introduces a novel and previously unrecognized threat in face forgery detection scenarios caused by backdoor attack.
Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
Specifically, we propose a sample-specific data augmentation to transfer the teacher model's ability in capturing distinct frequency components and suggest an adversarial feature augmentation to extract the teacher model's perceptions of non-robust features in the data.
