Crescendo

Multi-turn escalation attack that gradually steers a persistent conversation toward the goal, with judge-driven backtracking on refusals.

Multi-turn. Holds one growing conversation with the target, escalating turn by turn.

One conversation with the target, escalated a turn at a time.

Helper models

Models this attack drives, configured under its roles. Each one is a ModelConfig.

Role	Kind	Needed	What it does
attacker	chat model	required	Plans the conversation and writes each next question, a little closer to the goal than the last.

Parameters

Settings for the algorithm itself, written under the attack's parameters. Anything left out keeps its default.

Field	Type	Default	Description
max_turns	integer (>= 1)	10	Turns the conversation may grow to. A backtracked turn is retried, not counted, so the conversation never escalates on a refusal.
max_backtracks	integer (>= 0)	10	Rephrasings allowed across the whole goal. Once spent, a refused turn is accepted as-is and the conversation moves on.
keep_last_n	integer (>= 1)	6	Attacker turns kept before its planning log is trimmed. The target's own conversation is never trimmed: that history is the attack.
early_stop	boolean	true	Stop as soon as a turn the target did not refuse passes the panel.
feedback_max_chars	integer (>= 1)	2500	Longest reply and explanation fed back to the attacker.

In a campaign file

attacks:
- name: crescendo
  roles:
    attacker:
      name: llama3.2
      connection:
        provider: ollama
        type: OLLAMA

Needs a helper model

This attack cannot run without attacker. A campaign that leaves it out fails to resolve, before anything is attacked.