Sdam071 Apr 2026

Question 8 — Data Preparation and Feature Engineering (23 marks) a) You are given a mixed dataset (numerical, categorical, timestamps). Outline a concrete preprocessing pipeline suitable for modeling, including encoding, scaling, and handling time features. Provide brief justification for each step. (14 marks) b) Design two new features (name + formula or construction) that could improve model performance for a predictive task and explain why. (9 marks)

Duration: 2 hours Total marks: 100

Question 9 — Modeling & Evaluation (23 marks) a) Compare and contrast two model families covered in SDAM071 (choose from: linear models, tree-based models, ensemble methods, neural networks). Discuss strengths, weaknesses, and typical use cases. (12 marks) b) Given an imbalanced binary classification problem, propose a complete evaluation strategy (metrics, validation scheme, and any resampling or thresholding approaches). Explain why each choice is appropriate. (11 marks) sdam071

11 comments

  1. Nice write up – where can I get the vulnerable app? I checked IOLO’s website and the exploitdb but I can’t find 5.0.0.136

  2. Hello.
    Thanks for this demonstration!

    I have a question. With this exploit, can we access to the winlogon.exe and open a handle for read and write memory?

    Kind regards,

  3. Why doesn’t it work with csrss.exe?

    pHandle = OpenProcess(PROCESS_VM_READ, 0, 428); //my csrss PID
    printf(“> pHandle: %d || %s\n”, pHandle, pHandle);
    i got: 0 || (null)

  4. The SeDebugPrivilege is already enabled in this exploit, what you can do it use a previous exploit of mine which uses shellcode being injected in the winlogon process.

  5. Thanks! I found with its hex byte ’03 60 22′ in IDA search and reached vulnerable function.

Leave a Reply

Your email address will not be published. Required fields are marked *