Phases of Learning
Security Analysis
Framework
Exploratory Attacks
Causative Attacks
100

What are the three main components typically considered in a secure ML framework?

Data, model, and environment

100

What defines the attacker’s goals, knowledge, and capabilities?

Threat model

100

What is used to protect models from attacks?

Defense mechanism

100

What is the main goal of an exploratory attack?

Learning about the model without altering it

100

What is the attack where an adversary tries to replicate a model?

Model extraction

200

What is the attack that determines whether a data point was in the training set?

Membership inference

200

What is the attack where inputs are crafted to bypass detection during testing?

Evasion attack

200

What is the main strategy of a causative attack?

Poisoning the training data

200

In which phase do causative attacks typically occur?

Training phase

200

What type of attack alters training data to degrade model performance?

Data integrity attack

300

What is the attack where labels in the dataset are intentionally changed?

Label flipping

300

What are the two main categories of attacks in secure learning?

Both exploratory and causative

300

Which security property is targeted by exploratory attacks?

Confidentiality

300

What is the phase where data is cleaned and prepared before training?

Preprocessing

300

What is the phase where the trained model is evaluated or used for predictions?

Testing (or inference) phase