Performance Analysis
Appendix 545 A Details of datasets and architectures 546 A.1 Object Detection Image Dataset
We evaluate our method on three well-known model architectures:, i.e., SSD [ Named Entity Recognition, and Question Answering. Find more details in Table 5. Recall, ROC-AUC, and Average Scanning Overheads for each model. A value of 1 indicates perfect classification, while a value of 0.5 indicates To the best of our knowledge, there is no existing detection methods for object detection models. We evaluate the IoU threshold used to calculate the ASR of inverted triggers. However, a threshold of 0.7 tends to degrade the Different score thresholds are tested when computing the ASR of inverted triggers.
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
Work done during an internship at Tencent AI Lab.
United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
In recent years, deep neural networks (DNNs) have witnessed extensive applications, and protecting their intellectual property (IP) is thus crucial. As a noninvasive way for model IP protection, model fingerprinting has become popular.
SpatialPIN: Enhancing Spatial Reasoning Capabilities
To this end, we propose SpatialPIN, a framework that utilizes progressive prompting and interactions between VLMs and 2D/3D foundation models as "free lunch" to enhance spatial reasoning capabilities
