argus-redact 0.5.0

Encrypt PII, not meaning. Locally.

argus-redact

Encrypt PII, not meaning. Locally.

The privacy layer between you and AI. Your identity stays on your device — AI gets the meaning, not you.

from argus_redact import redact, restore

redacted, key = redact("王五在协和医院做了体检，手机[phone]", names=["王五"])
# "P-83811在[LOCATION]做了体检，手机138****5678"

llm_output = call_llm(redacted)     # LLM never sees real identities
restored = restore(llm_output, key)  # one line to get everything back

pip install argus-redact

Three Promises

	Promise	How
🛡️	Protected — your PII never leaves your device	3-layer local detection: regex → NER → local LLM
🧠	Usable — AI can still understand and help you	Pseudonym replacement preserves meaning and context
🔄	Reversible — you get everything back, intact	Per-message key, one-line restore

Other tools shred your PII — it's gone forever. argus-redact encrypts it with a different key every time. ETH Zurich research shows LLMs can deanonymize users for $1-4/person when pseudonyms are fixed. We generate fresh random keys per call — the cloud sees unrelated pseudonyms every time.

Privacy Levels

argus-redact evaluates your text from your perspective, not a regulator's:

🟢 Safe      — nothing about you is exposed
🟡 Caution   — contains personal info, not dangerous alone
🟠 Danger    — can narrow down to you specifically
🔴 Exposed   — directly identifies you

from argus_redact import redact

report = redact("身份证110101199003074610，手机[phone]，确诊糖尿病", report=True)
report.risk.level    # "critical"
report.risk.score    # 1.0
report.risk.reasons  # ("id_number (critical)", "phone (high)", "medical (critical)", ...)

This is what compliance frameworks don't tell you: how dangerous is it to share this specific text with AI?

Three Layers, Collaborative

Layer 1  Rust+Regex   phone, ID, bank card, email, self-reference, ...    <0.2ms
             │
         produce_hints() → text_intent, pii_density, self_reference_tier
             │
Layer 2  NER ← hints   locations, organizations, standalone names         10-100ms
Layer 3  Local LLM      implicit PII — symptoms→disease, behavior→belief  ~20s

Layers are not independent — L1 passes hints to L2, enabling collaborative detection. Instruction text ("帮我看看这段代码") skips NER entirely. High PII density lowers NER thresholds. Cross-layer agreement boosts confidence.

Unicode-hardened: NFKC normalization, zero-width stripping, Cyrillic/Greek confusable defense, Chinese digit detection (一三八零零一三八零零零 → detected as phone).

Core engine (regex matching, entity merging, restore, pseudonym generation) is written in Rust via PyO3 for maximum performance. Python handles orchestration, NER models, and LLM integration.

~47 PII types across 4 levels — from phone numbers to medical diagnoses, religious beliefs, political opinions. Default is mode="fast" (Layer 1 only, zero deps, sub-ms). Opt in: mode="ner" (+ NER models) → mode="auto" (all three layers).

Telemetry: ARGUS_PERF_LOG=perf.jsonl for per-call timing breakdown. Details →

Limitations & When NOT to Rely on This

argus-redact is a PII data minimization aid, not an anonymization or compliance certification:

• L1 fast (regex) matches well-defined formats. Novel or obfuscated variants, cross-field inference attacks pass through.
• L2 NER is statistical inference; out-of-distribution text (informal, typo-heavy, minority names) has higher miss rate. See benchmark results for measured numbers.
• No guarantee against adversarial inputs — attackers can craft text that evades detection.
• Not a GDPR / PIPL anonymization framework — anonymization is a compliance process decision, not a single-library output.

When to use argus-redact: reversible pseudonymization for LLM pipelines where you need redact() → LLM → restore() with zero PII crossing the network boundary.

When to consider alternatives: if you need one-way English PII masking with a single model call, OpenAI Privacy Filter and similar model-based maskers may fit better. argus-redact's niche is Chinese-optimized multi-layer detection + reversibility.

Combine argus-redact with audit logging, rate limiting, and upstream policy — no single layer is sufficient.

8 Languages

	zh	en	ja	ko	de	uk	in	br
Phone	✓	✓	✓	✓	✓	✓	✓	✓
National ID	MOD11-2 + 15位旧版	SSN	My Number	RRN	Tax ID	NINO	Aadhaar	CPF/CNPJ
Bank/Card	Luhn	Luhn	—	—	IBAN	—	PAN	—
Person names	HanLP	spaCy	spaCy	spaCy	spaCy	spaCy	spaCy	spaCy
Email	✓	✓	✓	✓	✓	✓	✓	✓

Mix freely: lang=["zh", "en", "de"]. Pass known names: names=["王一", "张三"].

Performance

Rust core (PyO3) — M1 Max, mode="fast":

Text	redact()	restore()	Throughput
Short (17 chars)	0.07ms	0.04ms	13,036 docs/sec
Medium (770 chars)	1.00ms	0.05ms	1,031 docs/sec
Long (10K chars)	22.2ms	0.05ms	45 docs/sec

Pre-built wheels for all major platforms — no Rust toolchain needed to install:

✓ Linux x86_64 (glibc + musl/Alpine)
✓ Linux aarch64 (Raspberry Pi + Alpine ARM)
✓ macOS (Apple Silicon + Intel)
✓ Windows x64
× Python 3.10 / 3.11 / 3.12 / 3.13

ai4privacy benchmark: Email P=95% R=94%. Chinese PII F1=97%. Benchmarks → | Performance →

North Star

Dimension	Current (v0.5.0)	Next milestone
Protected	~47 PII types, L1-L4. PII leak 0% across GPT-4o / Claude / Gemini. Cross-layer hints	Adversarial testing
Usable	PRvL U=100%. Pseudonym codes + realistic mode (pseudonym-llm zh)	en realistic (v0.5.1)
Reversible	PRvL R by task: reference 100%, extract 50%, creative 0% (by design)	Task-aware guidance
Compliance	PIPL ~85%, risk assessment + profiles	PIPL/GDPR/HIPAA (byproduct)
Coverage	8 langs, 4 LLMs benchmarked, 6 frameworks	Streaming realistic (v0.5.2)

Risk Assessment

# Assess risk before sending to AI
report = redact(text, report=True)
report.risk.level         # "critical"
report.risk.pipl_articles # ("PIPL Art.28", "PIPL Art.51", ...)
report.entities           # detected PII details
report.stats              # per-layer timing

# CLI
argus-redact assess <<< "身份证110101199003074610"

Compliance profiles: redact(text, profile="pipl") / "gdpr" / "hipaa". Type filtering: redact(text, types=["phone", "id_number"]) / types_exclude=["address"].

Realistic Redaction (pseudonym-llm profile)

Default redaction emits placeholder labels ([TEL-79329], P-164) — clear for audit, but breaks downstream LLM reasoning because the message structure is gone. The pseudonym-llm profile replaces PII with realistic-looking but reserved-range fake values (e.g., 19999... mobile, 999... ID, 999999... bank card). LLMs reason correctly; humans can still tell it's synthetic if they know the convention.

Each call returns three text forms sharing one key dict:

Form	Example	Use for
audit_text	请拨打 [TEL-79329] 联系 P-164	Compliance archive — placeholder labels are auditable
downstream_text	请拨打 19999123456 联系张明	LLM input — semantic structure preserved
display_text	请拨打 19999123456ⓕ 联系张明ⓕ	UI rendering — visible ⓕ marker prevents confusion

from argus_redact import redact_pseudonym_llm, restore

result = redact_pseudonym_llm("请拨打 13912345678 联系王建国")
result.downstream_text  # "请拨打 19999123456 联系张明"  → LLM
result.display_text     # "请拨打 19999123456ⓕ 联系张明ⓕ"  → UI
result.audit_text       # "请拨打 [TEL-79329] 联系 P-164"  → audit log

# Round-trip works on any of the three forms
restore(result.downstream_text, result.key)  # → original

# CLI emits all three forms as JSON
echo "请拨打 13912345678 联系王建国" | \
  argus-redact redact -k key.json --profile pseudonym-llm | \
  jq .downstream_text

Reserved ranges (zh): 199-99-XXXXXX mobile (199-99 sub-segment unassigned), 099- landline (no such area code), 999XXX ID address code (GB/T 2260 unassigned), 999999 bank BIN (银联 unassigned), 滨海市 fictional address. International: example.com (RFC 2606), 192.0.2.0/24 etc. (RFC 5737).

Argus Gateway integration: response headers should include X-Argus-Redact-Profile: pseudonym-llm; UI clients render display_text, LLM clients consume downstream_text. Storage of downstream_text as business truth is unsafe — it's synthetic by design.

⚠️ Realistic-mode output must not be re-redacted (it would corrupt the key dict). redact_pseudonym_llm will raise PseudonymPollutionError if called on already-faked input — call restore() first.

Full API → · Known limitations →

Integrations

	Install
LangChain / LlamaIndex / FastAPI	core
Presidio bridge	pip install argus-redact[presidio]
MCP Server (Claude Desktop / Cursor)	pip install argus-redact[mcp]
HTTP API Server	pip install argus-redact[serve]
Structured data (JSON / CSV)	core
Streaming restore	core
Docker	slim 157MB / full 5GB

Security

PII never leaves your device. Per-message keys prevent cross-request profiling. Full security model →

Meets PIPL · GDPR · HIPAA technical requirements as a byproduct of its privacy-first design. Details →

Documentation

Getting Started	Install, first redact/restore, key management
API Reference	All parameters, return types, streaming, structured data
CLI Reference	Commands, flags, serve, MCP server
Configuration	Per-type strategies, enterprise mask rules, false positive reduction
Sensitive Info	Taxonomy, privacy levels, roadmap
Architecture	Three-layer engine, cross-layer hints, pure/impure separation
Language Packs	Adding new languages
Security Model	Threat model, compliance, per-message keys
PRvL Standard	Open evaluation standard: Privacy × Reversibility × Language
Layer 3 Benchmark	LLM model comparison, prompt design, regulatory analysis
Benchmarks	Evaluation against 9 public PII datasets
Performance	Latency, throughput, benchmark results

Contributing

CONTRIBUTING.md — language packs, test scenarios, framework integrations welcome.

Contributors

Who	Contribution
@aiedwardyi	Brazilian Portuguese language pack (CPF, CNPJ, phone)

License

Apache 2.0