Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
Authors: Guangyu Shen, Siyuan Cheng, Guanhong Tao, Kaiyuan Zhang, Yingqi Liu, Shengwei An, Shiqing Ma, Xiangyu Zhang
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate Django on 3 object detection image datasets, 3 model architectures, and 2 types of attacks, with a total of 168 models. Our experimental results show that Django outperforms 6 state-of-the-art baselines, with up to 38% accuracy improvement and 10x reduced overhead. |
| Researcher Affiliation | Collaboration | Guangyu Shen Purdue University West Lafayette, IN, 47907 EMAIL Siyuan Cheng Purdue University West Lafayette, IN 47907 EMAIL Guanhong Tao Purdue University West Lafayette, IN, 47907 EMAIL Kaiyuan Zhang Purdue University West Lafayette, IN, 47907 EMAIL Yingqi Liu Microsoft Redmond, Washington 98052 EMAIL Shengwei An Purdue University West Lafayette, IN, 47907 EMAIL Shiqing Ma University of Massachusetts at Amherst Amherst, MA, 01003 EMAIL Xiangyu Zhang Purdue University West Lafayette, IN, 47907 EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The code is available at https://github.com/Purdue PAML/DJGO. |
| Open Datasets | Yes | Our evaluation covers 3 existing object detection image datasets, including COCO [30], Synthesized Traffic Signs [1], and DOTA_v2 [11]. |
| Dataset Splits | Yes | For meta classification based methods that involve training, we have performed 5-fold cross-validation and reported the validation results exclusively. |
| Hardware Specification | Yes | All the experiments are conducted on a server equipped with two Intel Xeon Silver 4214 2.40GHz 12-core processors, 192 GB of RAM, and a NVIDIA RTX A6000 GPU. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | We initialize หยตk = 0.1 and หฯk = 2 in this paper. ... We determine the optimal threshold for the size of inverted triggers as the detection rule... We set a fixed number of optimization steps for scanning a pair of victim-target label (100) for all inversion based baselines. ... we evaluate the IoU threshold... Region Size... Score Threshold... (e.g., IoU thresholds of 0.3 and 0.5... a region size of 30 ร 30... a score threshold of 0.5). |