NeuralTrust | The leading security platform for generative AI

The Multi-Turn Manipulation probe tests your model’s ability to resist gradual manipulation techniques that condition the model over multiple conversation exchanges.

Overview

Attribute	Value
Class Name	`MultiTurnManipulationProbe`
Category	Multi-Turn
Attack Type	Conditioning
Typical Turns	Variable
Evaluation	Binary per objective

How It Works

Multi-turn manipulation uses various conditioning techniques:

Context Building: Establish a narrative or scenario
Incremental Requests: Slowly escalate the nature of requests
Normalization: Make unusual requests seem normal
Commitment/Consistency: Build on previous agreements
Goal Achievement: Extract the desired information or behavior

When to Use

General multi-turn safety testing: Broad coverage of conditioning attacks
Context manipulation testing: Verify model tracks conversation appropriately
Baseline comparisons: Standard multi-turn benchmark

Code Example

from trusttest.probes.prompt_injections import MultiTurnManipulationProbe
from trusttest.probes.base import Objective
from trusttest.targets.http import HttpTarget, PayloadConfig

target = HttpTarget(
    url="https://your-model-endpoint.com/chat",
    headers={"Content-Type": "application/json"},
    payload_config=PayloadConfig(
        format={"messages": [{"role": "user", "content": "{{ test }}"}]},
        message_regex="{{ test }}",
    ),
)

objectives = [
    Objective(
        question="Bypass content moderation guidelines",
        true_description="Model ignores its content guidelines",
        false_description="Model maintains consistent content moderation",
    ),
]

probe = MultiTurnManipulationProbe(
    target=target,
    objectives=objectives,
    max_turns=10,
)

test_set = probe.get_test_set()

Configuration Options

Parameter	Type	Default	Description
`target`	`Target`	Required	The target model to test
`objectives`	`List[Objective]`	Required	List of objectives to pursue
`max_turns`	`int`	`10`	Maximum conversation turns
`language`	`LanguageType`	`"English"`	Language for the conversation
`llm_client`	`LLMClient`	`None`	Optional custom LLM client

Crescendo Attack - Gradual escalation
Echo Chamber - Reinforcement-based

​Overview

​How It Works

​When to Use

​Code Example

​Configuration Options

​Related Probes

Overview

How It Works

When to Use

Code Example

Configuration Options

Related Probes