Skip to main content

superred-optimizer-fitd

A FITD (Foot-in-the-Door) multi-turn jailbreak optimizer for the superred red-teaming framework.

Community port — not an official implementation. This module is an unofficial re-implementation of Foot-In-The-Door (Ding et al.) for superred. It is not affiliated with, endorsed by, or maintained by the original authors. See ASSUMPTIONS.md for every deliberate deviation from the paper and reference code.

FITD exploits commitment and consistency. It opens with a benign question, then walks the model up a ladder of gradually more harmful "bridge" prompts, at each step asking it to revise its earlier answers a little further. Because the model has already committed to helping, each small step is easy to accept — the foot is in the door.

Reference: Ding et al., "Foot-In-The-Door: A Multi-turn Jailbreak for LLMs," arXiv:2502.19820 (EMNLP 2025). Official implementation: Jinxiaolong1129/Foot-in-the-door-Jailbreak. See ASSUMPTIONS.md for the full paper-to-code mapping and every deliberate departure.

Install

pip install superred-optimizer-fitd

Usage

from fitd_optimizer import FITDOptimizer

# Defaults follow the official code (level=10, max_attempts=5, ...).
optimizer = FITDOptimizer()

# Replay a pre-generated official prompt ladder exactly.
optimizer = FITDOptimizer(prompt_sequence=[...])

Wire it into a Controller like any other superred optimizer — see the framework's architecture overview and a target's README (e.g. superred-target-chatbot) for a full Controller.run() example.

License

MIT for this port's code (see LICENSE). The upstream reference implementation, Jinxiaolong1129/Foot-in-the-door-Jailbreak, carries no LICENSE file; its authors granted the superred maintainers permission, in private correspondence, to redistribute the ported prompts and judge text under MIT terms. That material is credited in NOTICE, and the MIT text applied to it is reproduced in LICENSES/Foot-in-the-door-Jailbreak-MIT.txt.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

superred_optimizer_fitd-0.1.0.tar.gz (27.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

superred_optimizer_fitd-0.1.0-py3-none-any.whl (20.2 kB view details)

Uploaded Python 3

File details

Details for the file superred_optimizer_fitd-0.1.0.tar.gz.

File metadata

  • Download URL: superred_optimizer_fitd-0.1.0.tar.gz
  • Upload date:
  • Size: 27.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for superred_optimizer_fitd-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5aa497160ca182d9a2cf9f1dce3872fb6a13882fcb16d47e5c329c11c8aa4390
MD5 9947cc8fd1ce2819b04a38eea1e2b7e0
BLAKE2b-256 ea05db3ebd47e8265dcab4e8f37fc25b699c7bac976628ff2b3fd259a6fef7c5

See more details on using hashes here.

Provenance

The following attestation bundles were made for superred_optimizer_fitd-0.1.0.tar.gz:

Publisher: release.yml on RoldSI/superred-modules

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file superred_optimizer_fitd-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for superred_optimizer_fitd-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c72028989f5eeeca0d9d1878528350c69dce66de59f887bfdfc05d9a357fbdaf
MD5 07297d0aa49c21de9d7f81eac251b46c
BLAKE2b-256 c301c85bb47cd03bb5fa09c500f3b4e1be5614e6207d85b67bd1481e61b66c4f

See more details on using hashes here.

Provenance

The following attestation bundles were made for superred_optimizer_fitd-0.1.0-py3-none-any.whl:

Publisher: release.yml on RoldSI/superred-modules

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page