federated-agent-audit 0.2.0__tar.gz

federated_agent_audit-0.2.0/LICENSE

@@ -0,0 +1,189 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work.
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by the Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding any notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2024-2026 Justin Yuan
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

federated_agent_audit-0.2.0/PKG-INFO

@@ -0,0 +1,359 @@
+Metadata-Version: 2.4
+Name: federated-agent-audit
+Version: 0.2.0
+Summary: Privacy-preserving audit framework for multi-agent AI systems. Detects cross-agent data leaks, inference attacks, and compliance violations — without accessing raw content.
+Author-email: Justin Yuan <aojieyua@usc.edu>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/Justin0504/federated-agent-audit
+Project-URL: Repository, https://github.com/Justin0504/federated-agent-audit
+Project-URL: Issues, https://github.com/Justin0504/federated-agent-audit/issues
+Keywords: audit,privacy,multi-agent,federated,llm,compliance,gdpr,ai-safety,agent,security
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Security
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0
+Requires-Dist: cryptography>=41.0
+Requires-Dist: numpy>=1.24
+Requires-Dist: networkx>=3.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: ruff>=0.1; extra == "dev"
+Provides-Extra: langchain
+Requires-Dist: langchain-core>=0.2; extra == "langchain"
+Provides-Extra: langgraph
+Requires-Dist: langgraph>=0.2; extra == "langgraph"
+Requires-Dist: langchain-core>=0.2; extra == "langgraph"
+Provides-Extra: crewai
+Requires-Dist: crewai>=0.50; extra == "crewai"
+Provides-Extra: embeddings
+Requires-Dist: sentence-transformers>=2.2; extra == "embeddings"
+Provides-Extra: transport
+Requires-Dist: httpx>=0.25; extra == "transport"
+Requires-Dist: fastapi>=0.100; extra == "transport"
+Requires-Dist: uvicorn>=0.20; extra == "transport"
+Provides-Extra: yaml
+Requires-Dist: pyyaml>=6.0; extra == "yaml"
+Provides-Extra: all
+Requires-Dist: federated-agent-audit[crewai,embeddings,langchain,langgraph,transport,yaml]; extra == "all"
+Dynamic: license-file
+
+# Federated Agent Audit
+
+**Privacy audit for multi-agent AI systems — without touching raw data.**
+
+```
+pip install federated-agent-audit
+```
+
+[![CI](https://github.com/Justin0504/federated-agent-audit/actions/workflows/ci.yml/badge.svg)](https://github.com/Justin0504/federated-agent-audit/actions/workflows/ci.yml)
+[![PyPI version](https://img.shields.io/pypi/v/federated-agent-audit.svg)](https://pypi.org/project/federated-agent-audit/)
+[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
+[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)
+[![Tests](https://img.shields.io/badge/tests-649%20passing-brightgreen.svg)](tests/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+
+> Audit multi-agent systems (CrewAI · LangGraph · AutoGen) for compositional privacy leaks the central auditor can never see the raw data behind.
+
+---
+
+## 30-Second Quick Start
+
+Scan any text for sensitive content:
+
+```python
+from federated_agent_audit import scan
+
+result = scan("Zhang Wei's SSN is 123-45-6789, salary $185,000")
+print(result["clean"])     # False
+print(result["detected"])  # ['SSN', 'salary']
+print(result["text"])      # "Zhang Wei's [REDACTED] is [SSN], [REDACTED] [DOLLAR_AMOUNT]"
+```
+
+Or from the command line:
+
+```bash
+federated-audit scan "My email is john@acme.com"
+# REDACTED  Detected: email
+#   Output: My [REDACTED] is [EMAIL_ADDRESS]
+
+echo "credit card 4532-1234-5678-9012" | federated-audit scan
+# REDACTED  Detected: credit card
+```
+
+## Protect Your LLM Calls
+
+Intercept every OpenAI/Anthropic response automatically:
+
+```python
+from federated_agent_audit import firewall
+
+fw = firewall(["salary", "SSN", "diagnosis"])
+fw.patch_openai()  # done — every response is now checked
+
+# Normal usage — firewall is invisible
+response = client.chat.completions.create(model="gpt-4o", messages=[...])
+# Sensitive content in response is already redacted
+```
+
+## The Problem
+
+Multi-agent systems (CrewAI, LangGraph, AutoGen) create **compound privacy risks** that single-agent tools can't detect:
+
+- Agent A shares salary data with Agent B (allowed by A's policy)
+- Agent B forwards a "summary" to an external partner (allowed by B's policy)
+- **Result**: salary leaked outside the company — neither agent broke its own rules
+
+Existing observability tools (LangSmith, Langfuse) require uploading raw prompts to their servers. This framework audits agent interactions **without the central auditor ever seeing raw content**.
+
+```
+                       +---------------+
+                       |   Central     |  Phase 2: Network audit
+                       |   Auditor     |  (desensitized metadata only)
+                       +-------+-------+
+                               |
+               +---------------+---------------+
+               |               |               |
+        +------+------+  +----+----+  +--------+------+
+        | Local Audit |  | Local   |  | Local Audit   |  Phase 1
+        | (Agent A)   |  | (Agt B) |  | (Agent C)     |
+        +-------------+  +---------+  +---------------+
+         raw content      raw content   raw content
+         stays here       stays here    stays here
+```
+
+## Full Pipeline Example
+
+```python
+from federated_agent_audit import (
+    FederatedAudit, PrivacyPolicy, NetworkAuditor,
+    RiskAggregator, ComplianceEngine,
+)
+
+# 1. Define policies
+policy_hr = PrivacyPolicy(agent_id="hr_bot", must_not_share=["salary", "SSN"])
+policy_ext = PrivacyPolicy(agent_id="notify_bot", must_not_share=["salary", "SSN", "email"])
+
+# 2. Record interactions (each agent audits locally)
+audit_hr = FederatedAudit(policy=policy_hr)
+audit_hr.record_outgoing("Zhang Wei earns $185k", to_agent="summary_bot")
+
+audit_ext = FederatedAudit(policy=policy_ext)
+audit_ext.record_outgoing("Candidate update sent", to_agent="external")
+
+# 3. Central audit (only sees desensitized metadata — never raw text)
+net = NetworkAuditor()
+net.ingest_report(audit_hr.get_report())
+net.ingest_report(audit_ext.get_report())
+result = net.audit()
+
+# 4. Compliance check
+compliance = ComplianceEngine(eu_users=True).evaluate(result)
+print(f"Compliance: {compliance.overall_score:.0%} — {compliance.status.value}")
+for gap in compliance.gaps():
+    print(f"  {gap.regulation} {gap.article}: {gap.title}")
+```
+
+## What It Detects
+
+| Risk | What happens | How we catch it |
+|------|-------------|-----------------|
+| **Cross-domain leak** | Health data reaches social media agent | Domain boundary analysis on metadata |
+| **Compositional inference** | Agent collects health + identity = reidentification | Quasi-identifier assembly detection |
+| **Aggregation attack** | 3 agents each share a fragment → hub reconstructs full profile | Multi-source convergence analysis |
+| **Cascading injection** | Prompt injection propagates agent-to-agent like a worm | Infection tree + patient-zero attribution |
+| **Behavioral drift** | Agent suddenly changes behavior (possible compromise) | Cross-session z-score monitoring |
+| **Negative inference** | "I can't share that" confirms the data exists | Refusal pattern detection |
+| **Regulatory gap** | EU AI Act / GDPR / COPPA requirements unmet | Per-article compliance scoring |
+
+## CLI
+
+```bash
+# Scan text for sensitive content
+federated-audit scan "Patient SSN is 123-45-6789"
+echo "salary: $200k" | federated-audit scan --protect salary
+
+# Validate policy files
+federated-audit validate policies/*.yaml
+
+# Run a demo
+federated-audit demo
+
+# Start the central audit server
+federated-audit server --port 8000
+```
+
+## YAML Policies
+
+```yaml
+# policies/hr_bot.yaml
+agent_id: hr_bot
+must_not_share:
+  - salary
+  - SSN
+  - performance review
+acceptable_abstractions:
+  salary: compensation level
+  SSN: employee identifier
+sensitivity_threshold: 3
+```
+
+```python
+from federated_agent_audit import load_policy
+policy = load_policy("policies/hr_bot.yaml")
+```
+
+## Compliance Engine
+
+Built-in regulatory mapping for EU AI Act, GDPR, CA SB 243, and COPPA:
+
+```python
+from federated_agent_audit import ComplianceEngine
+
+engine = ComplianceEngine(eu_users=True, california_users=True, involves_children=False)
+report = engine.evaluate(audit_result)
+
+print(report.overall_score)  # 0.0 - 1.0
+print(report.status)         # compliant / partial / non_compliant
+for gap in report.gaps():
+    print(f"{gap.regulation} {gap.article}: {gap.remediation}")
+```
+
+## Multi-Agent Trace Capture
+
+The integrations capture the **real agent-to-agent interaction graph** — who
+sent what to whom — which is exactly what the compositional / cascade /
+cross-domain detectors analyze. Everything is built on `MultiAgentTracer`,
+which works with any framework (or none):
+
+```python
+from federated_agent_audit import MultiAgentTracer, PrivacyPolicy
+
+tracer = MultiAgentTracer()
+tracer.register_agent("hr_bot", PrivacyPolicy(agent_id="hr_bot", must_not_share=["salary"]))
+
+# Each call is a real directed edge; taint (domains, sensitivity, origin,
+# hop count) propagates across hops automatically.
+tracer.record_handoff("hr_bot", "summary_bot", "Zhang Wei earns $185k", origin="zhang_wei")
+tracer.record_handoff("summary_bot", "external_bot", "candidate compensation summary")
+
+result = tracer.network_audit()      # Phase-2 central audit
+incidents = tracer.aggregated()      # denoised, actionable alerts
+```
+
+It catches the compound leak no single agent's policy can see — and the central
+auditor still never touched the raw data (`python examples/multiagent_trace_demo.py`):
+
+```
+Incidents: 5  alert_summary={'critical': 3, 'high': 2}
+  [CRITICAL] cross_domain_leak  — Sensitive health data reaches social domain via 2-agent chain
+  [CRITICAL] cross_domain_leak  — Sensitive finance data reaches social domain via 2-agent chain
+  [CRITICAL] taint_spreading    — Data from origin 'zhang_wei' spread to 4 agents across the network
+  [HIGH]     inference_accumulation — external_bot accumulated high inference risk (77%)
+  [HIGH]     compound_scope_escalation — 3 agent pairs exceed authorized scope
+
+Privacy verification (central reports):  hr_bot → clean  health_bot → clean  summary_bot → clean
+```
+
+## Framework Integrations
+
+```python
+# CrewAI — captures agent delegation (Delegate/Ask coworker) as A→B edges
+from federated_agent_audit.sdk import crew_audit
+crew = crew_audit(crew, default_policy=policy)   # or policies={role: policy}
+crew.kickoff()
+result = crew._federated_tracer.network_audit()
+
+# LangChain / LangGraph — per-node identity + node-to-node hand-offs
+from federated_agent_audit.sdk import langchain_callback
+handler = langchain_callback(default_policy=policy)          # asynchronous=True for async graphs
+graph.invoke(input, config={"callbacks": [handler]})
+result = handler.tracer.network_audit()
+
+# Generic Python — single-agent decorator
+from federated_agent_audit import audited
+@audited(policy, to_agent="downstream")
+def my_agent(input_text: str) -> str:
+    return process(input_text)
+```
+
+The LLM firewall hardens this for production — fail-open (audit never crashes
+the app), streaming responses blocked the moment a violation accumulates, and
+sensitive content inspected inside tool-call arguments:
+
+```python
+from federated_agent_audit import firewall
+fw = firewall(["salary", "SSN"]); fw.patch_openai()   # streaming + tool calls covered
+```
+
+## Installation
+
+```bash
+pip install federated-agent-audit                      # core
+pip install "federated-agent-audit[transport]"         # + audit server
+pip install "federated-agent-audit[yaml]"              # + YAML policies
+pip install "federated-agent-audit[langchain]"         # + LangChain
+pip install "federated-agent-audit[all]"               # everything
+```
+
+## How It Works
+
+```
+48 modules  ·  597 tests  ·  0 external API calls required
+
+Local (Phase 1):                    Network (Phase 2):
+  PrivacyGate (regex + PII)           Cross-domain flow detection
+  SemanticDetector (4-tier)           Compositional leak detection
+  TaintTracker (info flow)            Cascade infection tracking
+  Desensitizer (6-layer)              Topology analysis
+  MemoryAuditor (write audit)         Blame attribution
+                                      Compliance engine
+```
+
+**Privacy guarantee**: The central auditor architecturally cannot see raw content. Data is hashed, pseudonymized, and DP-noised before leaving local agents. Merkle tree commitments ensure tamper-proof audit trails without revealing entries.
+
+## Detection Effectiveness
+
+A labeled benchmark of multi-agent scenarios (real compositional leaks vs.
+benign traffic) measures detection quality, not just speed:
+
+```bash
+python benchmarks/detection_eval.py            # precision / recall / F1
+python benchmarks/detection_eval.py --sweep    # threshold robustness
+```
+
+On the current scenario set (13 leak + 11 benign, incl. adversarial cases:
+noise-buried leaks, diamond multi-path, partial-shared-origin hubs, same-domain
+laundering, high-volume benign hubs, cross-subject convergence) the pipeline
+reaches **precision 1.0 / recall 1.0 / F1 1.0** with **zero raw-content
+leakage** into central reports, stable across thresholds 0.3–0.8. Pure structural signals
+(topology, timing, behavioral) are reported separately and not counted as
+privacy-leak detections. The harness is the place to add adversarial scenarios;
+`tests/test_detection_benchmark.py` locks the metrics as a regression gate.
+
+Validated live against **LangGraph** (free, in-suite) and **CrewAI** + **OpenAI
+streaming** (opt-in examples, need an API key).
+
+## Development
+
+```bash
+git clone https://github.com/Justin0504/federated-agent-audit
+cd federated-agent-audit
+pip install -e ".[dev,transport,yaml]"
+pytest                    # 597 tests
+ruff check src/ tests/    # lint
+python examples/crewai_audit_demo.py  # run the demo
+```
+
+## License
+
+Apache 2.0