mirror of
https://github.com/guillaumemeyer/watermarks-remover.git
synced 2026-08-22 13:11:57 +02:00
Guillaume Meyer (The Opinionated Man)andGitHub
09e64c4ded
* feat: optional MarkLLM text-watermark verification harness Add an optional external backend wrapping THU-BPM/MarkLLM (Apache-2.0) so a specific statistical text-watermark scheme (KGW / SynthID-Text) can be verified before/after a Layer B rewrite. - detect_text_watermark.py: detect/watermark subcommands, external checkout at a pinned commit, exit codes 0/1/2/3, --json - rewrite_text.py --markllm-scheme: before/after detection around the rewrite, reports a `cleared` flag; never fails the rewrite when the backend is unavailable - setup_markllm.sh + requirements-markllm.txt (pinned deps) + Dockerfile.markllm + Makefile bootstrap/smoke/docker targets - tests/test_markllm_detect.py: 16 mock-based cases (no torch in CI) - Docs: verification-harness caveat (same-config-only, not a vendor-detector oracle) in README, SKILL.md, removal-matrix, vendor-notes * chore: tidy merged Unreleased changelog list * security: harden the MarkLLM harness (offline, caps, supply-chain) Addresses the PR security review: - detect_text_watermark.py: --offline loads the scoring model from the HF cache only (local_files_only + HF_HUB_OFFLINE, no remote code), and the algorithm config is capped at 1 MiB so a crafted huge file is refused before either this script or upstream reads it into memory - rewrite_text.py: WATERMARKS_MARKLLM_RLIMIT_AS (env, POSIX) optionally applies RLIMIT_AS to the MarkLLM subprocess; off by default because torch/CUDA needs large address spaces - Dockerfile.markllm: drop the unpinned torch install (it is pinned in requirements-markllm.txt) and verify the cloned upstream commit SHA - tests: offline flag, config-too-large, and preexec/rlimit cases - docs: hardening knobs in README + SKILL.md; changelog updated
77 lines
2.8 KiB
Makefile
77 lines
2.8 KiB
Makefile
.PHONY: test smoke smoke-synthid bootstrap-synthid docker-synthid-build docker-synthid-help \
|
|
smoke-ctrlregen bootstrap-ctrlregen docker-ctrlregen-build docker-ctrlregen-help \
|
|
smoke-markllm bootstrap-markllm docker-markllm-build docker-markllm-help install-skill clean
|
|
|
|
SCRIPTS := skills/remove-ai-marks/scripts
|
|
PYTHON ?= $(shell if [ -x .venv/bin/python ]; then echo .venv/bin/python; else echo python3; fi)
|
|
|
|
test:
|
|
$(PYTHON) -m pytest
|
|
|
|
smoke:
|
|
-python3 $(SCRIPTS)/inspect_text.py tests/fixtures/sample_watermarked.txt
|
|
python3 $(SCRIPTS)/clean_text.py tests/fixtures/sample_watermarked.txt -o /tmp/wm.cleaned.txt --stats
|
|
python3 $(SCRIPTS)/rewrite_text.py tests/fixtures/sample_watermarked.txt --backend print-prompt >/dev/null
|
|
-python3 $(SCRIPTS)/inspect_file.py tests/fixtures/sample_ai.md
|
|
python3 $(SCRIPTS)/clean_file.py tests/fixtures/sample_ai.md -o /tmp/sample_ai.cleaned.md
|
|
python3 $(SCRIPTS)/clean_file.py tests/fixtures/sample_ai.html -o /tmp/sample_ai.cleaned.html
|
|
python3 $(SCRIPTS)/clean_file.py tests/fixtures/sample_meta.svg -o /tmp/sample_meta.cleaned.svg
|
|
@echo "smoke ok"
|
|
|
|
smoke-synthid:
|
|
@if [ -z "$(REVERSE_SYNTHID_DIR)" ]; then \
|
|
echo "smoke-synthid skipped (set REVERSE_SYNTHID_DIR)"; \
|
|
else \
|
|
$(PYTHON) $(SCRIPTS)/score_synthid.py --help >/dev/null && echo "score_synthid adapter present"; \
|
|
fi
|
|
|
|
bootstrap-synthid:
|
|
./skills/remove-ai-marks/scripts/setup_synthid.sh
|
|
|
|
docker-synthid-build:
|
|
docker build -f Dockerfile.synthid -t watermarks-remover-synthid-scorer .
|
|
|
|
docker-synthid-help:
|
|
docker run --rm watermarks-remover-synthid-scorer --help
|
|
|
|
smoke-ctrlregen:
|
|
@if [ -z "$(NOAI_WATERMARK_DIR)" ]; then \
|
|
echo "smoke-ctrlregen skipped (set NOAI_WATERMARK_DIR)"; \
|
|
else \
|
|
$(PYTHON) $(SCRIPTS)/clean_ctrlregen.py --help >/dev/null && echo "clean_ctrlregen adapter present"; \
|
|
fi
|
|
|
|
bootstrap-ctrlregen:
|
|
./skills/remove-ai-marks/scripts/setup_ctrlregen.sh
|
|
|
|
docker-ctrlregen-build:
|
|
docker build -f Dockerfile.ctrlregen -t watermarks-remover-ctrlregen .
|
|
|
|
docker-ctrlregen-help:
|
|
docker run --rm watermarks-remover-ctrlregen --help
|
|
|
|
smoke-markllm:
|
|
@if [ -z "$(MARKLLM_DIR)" ]; then \
|
|
echo "smoke-markllm skipped (set MARKLLM_DIR)"; \
|
|
else \
|
|
$(PYTHON) $(SCRIPTS)/detect_text_watermark.py --help >/dev/null && echo "detect_text_watermark adapter present"; \
|
|
fi
|
|
|
|
bootstrap-markllm:
|
|
./skills/remove-ai-marks/scripts/setup_markllm.sh
|
|
|
|
docker-markllm-build:
|
|
docker build -f Dockerfile.markllm -t watermarks-remover-markllm .
|
|
|
|
docker-markllm-help:
|
|
docker run --rm watermarks-remover-markllm --help
|
|
|
|
install-skill:
|
|
mkdir -p $(HOME)/.grok/skills
|
|
ln -sfn $(CURDIR)/skills/remove-ai-marks $(HOME)/.grok/skills/remove-ai-marks
|
|
@echo "linked -> $(HOME)/.grok/skills/remove-ai-marks"
|
|
|
|
clean:
|
|
find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true
|
|
rm -rf .pytest_cache .venv
|