medium · FRM Part 2 Current Issues
Why is 'adversarial robustness' a higher concern for AI models than for traditional linear models in finance?
- Traditional linear models are considered entirely immune to any and all forms of adversarial manipulation or gaming attempts.
- AI models have high-dimensional decision boundaries that can be exploited by small, targeted perturbations (inputs) to flip a prediction.
- AI models are deployed exclusively within cloud computing environments, whereas linear regression models always run strictly on-premises.
- AI models invariably contain far fewer parameters than traditional linear regression models, which inherently makes them more fragile and easier to exploit.
Sign up free to see the explanation and track your rank →
More FRM Part 2 Current Issues practice
- According to the BCBS standard for cryptoassets, a bank's to… — What is this limit?
- What primary balance (as a % of GDP) is required to stabilize the debt-to-GDP ratio?
- SVB's management removed interest rate hedges in 2022. According to the Economic Value of
- In monitoring model stability, which metric is commonly used to quantify the shift in dist
- What does a SHAP value of zero for a specific feature in a credit scoring model imply?
- A bank provides a 'NAV facility' to a private equity fund. If the fund's underlying assets
- What is the bank's primary ongoing obligation to regulators regarding this new model?
- If the firm's EBITDA declines, when can the lender intervene?