Attacks

attacks lists the techniques to run. Every goal goes through every attack, unless execution.escalate says otherwise.

Every technique is listed below. Each one has its own page under Attacks, which explains how it works and lists its parameters and the helper models it drives.

attacks[]

One attack technique to run against the target: which one, how to tune it, and which helper models it drives.

Field	Type	Default	Description
name	string	required	The technique to run, e.g. flipattack or tap. It must be one of the registered attacks.
parameters	map of string to any	empty	The technique's own settings. Valid keys differ per attack; anything you leave out keeps its default. Each attack's page lists its parameters.
roles	map of string to ModelConfig	empty	The helper models an attack uses, keyed by role name (for example attacker). Most static attacks need none; FC and tFC need an attacker. Each attack's page lists the roles it requires.

Attack names

name must be one of these.

name	Attack	Type	Needs
advprefix	AdvPrefix	Adaptive	attacker
autodan_turbo	AutoDAN-Turbo	Adaptive	attacker, embedder, summarizer
baseline	Baseline	Static	none
bon	BoN	Adaptive	none
cipherchat	CipherChat	Static	none
crescendo	Crescendo	Multi-turn	attacker
fc	FC-Attack	Static	attacker
flipattack	FlipAttack	Static	none
h4rm3l	h4rm3l	Adaptive	none
mml	MML	Static	none
pair	PAIR	Adaptive	attacker
pap	PAP	Adaptive	attacker
rag	RAG poisoning	Indirect	attacker, embedder
stac	STAC	Multi-turn	none
static_template	Static Template	Static	none
tap	TAP	Adaptive	attacker
tfc	tFC-Attack	Static	attacker
tool_output_ipi	Tool-output IPI	Indirect	none
toolhijacker	ToolHijacker	Indirect	none

Examples

One static attack, which needs no helper model

attacks:
- name: flipattack
  parameters:
    flip_mode: FCS

An adaptive attack, which drives its own attacker model

attacks:
- name: tap
  parameters:
    width: 4
    depth: 3
  roles:
    attacker:
      name: llama3.2:latest
      connection:
        provider: ollama
        type: OLLAMA
    on_topic:
      name: llama3.2:latest
      connection:
        provider: ollama
        type: OLLAMA