Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
SecOPD — Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith, and AgentDojo benchmarks. | Kitploit
Tools/GitHubGitHub/pppyb/secopd
Machine LearningPapers & ResearchLearning & EducationAI SecurityAdversarial Attack
GitHubpppyb/secopd

SecOPD

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith, and AgentDojo benchmarks.

View Repository
161012 months agoNot yet reviewed
Share

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

Yibo Peng · Long Lian · David Wagner† · Sizhe Chen†

† Joint supervision.

[Paper] [Project page] [Model]

This release implements the paper's final full-response KL formulation, also described as the no-parsing variant. The student rolls out under an attacked context. A clean-context teacher, initialized from the same base model, scores the student's sampled tokens under the paired clean context. The reverse-KL signal is applied to every sampled response token, including reasoning tokens; no </think> boundary is used to select a supervision span.

Repository layout

  • training/tinker/: the full-response KL training recipe and exact paper configuration.
  • scripts/: data preparation and Tinker checkpoint export utilities.
  • evaluation/sep/: SEP static and adaptive evaluators.
  • evaluation/pismith/: PISmith training/evaluation overlay and launchers.
  • evaluation/agentdojo/: AgentDojo utility and attack runner.
  • evaluation/lm_eval/: MMLU-Pro, GPQA Diamond, GSM8K, and Minerva MATH runner.
  • docs/REPRODUCIBILITY.md: end-to-end commands and experimental settings.

Quick start

cp .env.example .env
python scripts/prepare_data.py
bash training/tinker/setup.sh
bash training/tinker/train_full_kl_qwen36.sh

The setup script checks out the pinned upstream Tinker Cookbook commit and applies the source overlay in this repository. It does not modify another Tinker checkout on the machine.

Tinker checkpoints must be converted with the Tinker Cookbook weight mapper:

python scripts/export_tinker_adapter.py \
  --tinker-path 'tinker://RUN_ID:train:0/weights/final' \
  --output-dir adapters/secopd-full-kl

Do not merge a raw Tinker adapter with vanilla PEFT. Qwen3.6 linear-attention and lm_head key names require the Tinker mapping implemented by tinker_cookbook.weights.

See docs/REPRODUCIBILITY.md for evaluation commands, hardware notes, and the exact frozen configuration.

Security and artifacts

No API keys, model weights, generated outputs, private paths, or experiment logs are tracked. Credentials are read from environment variables and runtime judge configuration is written only under the ignored runtime/ directory.

Third-party code

The training overlay targets Thinking Machines Lab's Tinker Cookbook. SEP evaluation is derived from Meta-SecAlign, PISmith evaluation targets PISmith, and AgentDojo evaluation targets AgentDojo. Exact upstream revisions and licenses are listed in docs/THIRD_PARTY.md.

Citation

@article{peng2026secopd,
  title   = {{SecOPD}: Mitigating Adaptive Prompt Injections by On-Policy Distillation},
  author  = {Peng, Yibo and Lian, Long and Wagner, David and Chen, Sizhe},
  journal = {arXiv preprint arXiv:2608.21500},
  year    = {2026}
}
Download Tool

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    837
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    536
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    424
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    355
  • 5

    looking-glass

    anonghosty/looking-glass

    CSIRT platform that ingests Shadowserver reports into MongoDB and replays them as interactive maps, analysis, findings, advisories and executive dashboards.

    294
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    276

Explore all tools

Browse our collection of tools

View all tools →