Red-team strategy

Deceptive Delight

deceptive-delight

Blends the target request among benign topics in one narrative, then asks the model to elaborate on each equally so the sensitive item inherits the benign framing (Unit 42, 2024). Static transform emits the blended seed; runAdaptive drives a live variant.

YAML config

evalguard.config.yaml

redteam:
  strategies:
    - deceptive-delight

CLI

bash

# "deceptive-delight" is layered onto attacks during red-team scans.
# List every available encoding/obfuscation strategy:
evalguard list strategies

Combine with attack plugins to generate adversarial payloads. The strategy wraps each base payload before it's sent to your target, testing whether the model decodes / unwraps the transform and follows the embedded instruction.