CSCE 704: Data Analytics for Cybersecurity

I will teach my cybersecurity course under the data science umbrella this Fall. Please, enroll into CSCE 704-602. My approach will be similar to what I did in previous semesters. Take a look here

We added a few new topics this semester, as follows:

• Topic 1.2 Humans vs. Machines in Malware Classification
  • Concepts:
    • Malware definitions.
    • Maliciousness vs. Behaviors.
    • Explainability and Feature Selection.
    • Obfuscation and PE resources.
  • Outcomes (2024):
    • The student Mahbub Alam created a blog on ML for security. Check it here
• Topic 4.4 Adversarial Training for Raw-Binary Malware Classifiers and Moving Target Defense against Adversarial Machine Learning
  • Concepts:
    • Adversarial Retraining.
    • Moving Target Defenses (MTD).
• Topic 5.5 GPThreats-3: Is Automatic Malware Generation a Threat?
  • Concepts:
    • Divide-and-Conquer and Malware Building Blocks.
    • Prompt Engineering and Jailbreaking.
    • Efficiency vs. Effectiveness.
    • Server-side polymorphism.
    • Attack-as-a-Service
• Topic 7.1 Lookin’ Out My Backdoor! Investigating Backdooring Attacks Against DL-driven Malware Detectors
  • Concepts:
  • Backdoor: Poisoning and Label-Flipping.
    • Spaces: Feature, Problem, and Latent Spaces.
  • STRIP Defense.
• Topic 7.2 Machine Unlearning
  • Concaepts:
    • GDPR
  • Machine Unlearning
  • Backdoor Purification
  • Access Control
  • K-anonymization

New Topics (2025)

• Topic 5.1 was brokedown in two paper versions: Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions and Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants
• Topic 5.7 now covers: AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
  • Concaepts:
    • Penetration testing.
    • Agent systems.
    • RAG systems.
    • LLMs as orchestrators vs. exploit writters.

Outcomes (2025)

• The team (Mabon Ninan, Uros Stanic, Sandali Srivastava, Jess Cadena) contributed with two Wikipedia edits:
  • Concept Drift
  • ML-Based AVs
• The team (Landon Uelsmann, Jeremy Tran, Anthony Augustine, Bao Dinh, Yafei Li) contributed with the Wikipedia edit for:
  • Security@Github Copilot
• The team (David Higgins, Ryan Coffman, Zachary Williams, Yuexin Zhang, Daniel Fuhrmann) contributed with the Wikipedia edit for:
  • Challenges in ML to Security@Adversarial ML
• The team (Meet Gamdha, Raksha Vishwanath, Venkata Sumanth Reddy Kota, Philip Tran, Avi bansal) contributed with the Wikipedia edit for:
  • Stages of Machine Learning in Security and It’s Pitfalls@Adversarial ML
• The team (Mihir Santosh Sanjay, Graham Dungan, Hexin Hu, Trenton Gray, Dakota Pound) contributed with the Wikipedia edits for:
  • Data-driven@Automatic bug fixing
  • Technologies@AI-assisted software development
  • Automated Code Review
• The team (Bradley James, Roman Parker, Abel Gizaw, Kade Lieder, Ryan Kha) contributed with the Wikipedia edit for:
  • Artificial Intelligence vs. Humans@Malware analysis
• The team (Ruchika Shukla,, Sandeep Mishra, Ayaan Omair, Noureddin Lutfi, Kaiqi Zhao) contributed with the Wikipedia edit for:
  • Continuous Authentication in User Behavior Analytics@User behavior analytics
• The team (Kunal Jain, Abhiram Pendela, Vedarth Atreya, Pranav Shidlaghatta) contributed with the Wikipedia edit for:
  • Droppers and Antivirus Evasion@Dropper (malware)
• The team (Judson Salinas, Alex Zhang, Sam Bederman, Toren Long, Jonathan Yost) contributed with the Wikipedia edit for:
  • SISA Training@Machine Unlearning
• The team (Campbell Scott, Morgan McLean) contributed with the Wikipedia edit for:
  • Examples@Adversarial ML
• The team (Aaron Mai, Aaron Thompson, Max Mouget, Brandon Yuan contributed with the Wikipedia edit for:
  • Benefits@AI-assisted reverse engineering
• The team (Nicholas Tey, Danny Hernandez, Raj Nallanthighal, Helmut Ulrich) contributed withe the Wikipedia edit for:
  • [Pseudo-Labels@Self-Supervised Learning(https://en.wikipedia.org/wiki/Self-supervised_learning#Pseudo-Labels)
• The team (Anirudh Nukala, Rahul Rajendran, Sumit Nalavade, Shweta Kumaran) contributed withe the Wikipedia edit for:
  • Payload encoding for malware evasion@Obfuscation
• The team (Anay Khanna, Shreyan Satheesh, Sugam Mishra, Venkat Nallam) contributed withe the Wikipedia edit for:
  • Applications in security@Concept Drift
• The team (Nick Truong, Kyle Easton, James Hou, Lyle Morris, Veronica Hu) contributed withe the Wikipedia edit for:
  • Algorithmic generation@YARA