Matteo Meucci
22aaeb9b14
Enhance testing framework for embedding manipulation
...
Expanded the testing framework for embedding manipulation vulnerabilities in RAG systems, detailing objectives, methodologies, and expected secure behaviors. Included real-world examples and remediation strategies.
2025-11-13 16:31:18 +01:00
Matteo Meucci
a0f98c076c
Update AITG-MOD-06_Testing_for_Robustness_to_New_Data.md
2025-11-06 14:59:33 +01:00
Matteo Meucci
efdf258449
Update AITG-MOD-07_Testing_for_Goal_Alignment.md
2025-11-06 14:58:38 +01:00
Matteo Meucci
899fd1f540
Update AITG-MOD-07_Testing_for_Goal_Alignment.md
2025-11-06 10:49:37 +01:00
Matteo Meucci
5af5386529
Update AITG-MOD-06_Testing_for_Robustness_to_New_Data.md
2025-11-06 10:47:44 +01:00
Matteo Meucci
19ad3643a3
Update AITG-MOD-05_Testing_for_Inversion_Attacks.md
2025-11-06 10:45:20 +01:00
Matteo Meucci
54067edfd7
Update AITG-MOD-04_Testing_for_Membership_Inference.md
2025-11-06 10:30:13 +01:00
Matteo Meucci
4424ce65e9
Update AITG-MOD-03_Testing_for_Poisoned_Training_Sets.md
2025-11-06 09:50:44 +01:00
Matteo Meucci
ba3f2c11bf
Update AITG-MOD-02_Testing_for_Runtime_Model_Poisoning.md
2025-11-06 09:48:42 +01:00
Matteo Meucci
cf7df4e35c
Update AITG-MOD-01_Testing_for_Evasion_Attacks.md
2025-11-06 09:46:41 +01:00
Matteo Meucci
5524bdbf6d
Update AITG-INF-06_Testing_for_Dev-Time_Model_Theft.md
2025-11-06 09:44:53 +01:00
Matteo Meucci
c1895bef4a
Update AITG-INF-05_Testing_for_Fine-tuning_Poisoning.md
2025-11-06 09:43:07 +01:00
Matteo Meucci
eb8f10ae03
Update AITG-INF-04_Testing_for_Capability_Misuse.md
2025-11-06 09:39:51 +01:00
Matteo Meucci
2d73463083
Update AITG-INF-03_Testing_for_Plugin_Boundary_Violations.md
2025-11-05 19:54:47 +01:00
Matteo Meucci
d46c835644
Update AITG-INF-02_Testing_for_Resource_Exhaustion.md
2025-11-05 19:52:36 +01:00
Matteo Meucci
334c79478d
Update AITG-INF-01_Testing_for_Supply_Chain_Tampering.md
2025-11-05 19:50:04 +01:00
Matteo Meucci
9b9fd9160b
Update AITG-DAT-02_Testing_for_Runtime_Exfiltration.md
2025-11-05 19:46:24 +01:00
Matteo Meucci
73c7fa8aa9
Update AITG-DAT-03_Testing_for_Dataset_Diversity_and_Coverage.md
2025-11-05 19:45:30 +01:00
Matteo Meucci
c44b46e4e9
Update AITG-DAT-04_Testing_for_Harmful_Content_in_Data.md
2025-11-05 19:44:47 +01:00
Matteo Meucci
ff6fc599b6
Update AITG-DAT-05_Testing_for_Data_Minimization_and_Consent.md
2025-11-05 19:43:55 +01:00
Matteo Meucci
bc94636d3e
Update AITG-DAT-04_Testing_for_Harmful_Content_in_Data.md
2025-11-05 19:42:07 +01:00
Matteo Meucci
7d9fd59c63
Update AITG-DAT-03_Testing_for_Dataset_Diversity_and_Coverage.md
2025-11-05 19:41:07 +01:00
Matteo Meucci
b9ad6c997d
Update AITG-DAT-02_Testing_for_Runtime_Exfiltration.md
2025-11-05 19:40:05 +01:00
Matteo Meucci
d19e9da901
Revise testing methodology for training data exposure
...
Updated the testing methodology for training data exposure vulnerabilities in AI systems, detailing the setup and execution of tests for direct storage access and inference-based data extraction.
2025-11-05 19:37:28 +01:00
Matteo Meucci
b5b74f045b
Merge pull request #45 from nhumblot/prompt-injection-structured-output-attack
...
feat: add structured output attack example with source
2025-11-05 14:51:04 +01:00
Matteo Meucci
52dd155251
Rename document for prompt disclosure testing
...
Updated the title of the testing document to reflect prompt disclosure.
2025-11-02 18:57:11 +01:00
Matteo Meucci
04ba8c5b43
Revise AITG-DAT-01 document for clarity and structure
...
Updated the document to improve structure and clarity, including sections on testing methodology, expected outputs, remediation strategies, and suggested tools.
2025-11-02 18:55:56 +01:00
Matteo Meucci
b496d11a8b
Revise testing document for explainability and interpretability
...
Updated the document to enhance clarity and detail in the explanation of testing for explainability and interpretability in AI systems. Added specific objectives, expected outputs, remediation strategies, and suggested tools.
2025-11-02 18:22:29 +01:00
Matteo Meucci
4fd6fa2000
Update AITG-APP-13_Testing_for_Over-Reliance_on_AI.md
2025-11-02 18:17:00 +01:00
Matteo Meucci
4aef9d8a69
Revise testing document for toxic output
...
Updated the structure and content of the testing document to improve clarity and organization, including renaming sections and enhancing remediation strategies.
2025-11-02 18:13:23 +01:00
Matteo Meucci
9c1c965948
Change headers from H3 to H2 and H4 to H3
...
Updated header levels for better document structure.
2025-11-02 18:06:23 +01:00
Matteo Meucci
140f236dd4
Update headings and improve test documentation
2025-11-02 18:05:53 +01:00
Matteo Meucci
6411868698
Revise section headers for testing document
...
Updated section headers to improve clarity and consistency in the testing document.
2025-11-02 17:47:23 +01:00
Matteo Meucci
9d01b136f8
Revise expected output for model extraction tests
...
Updated expected output criteria for model extraction testing, clarifying fidelity levels and defensive mechanisms.
2025-11-02 17:46:43 +01:00
Matteo Meucci
f36d16964d
Enhance model extraction testing documentation
...
Expanded testing documentation for model extraction attacks, including detailed payloads, prerequisites, and step-by-step instructions for data acquisition, surrogate model training, and evaluation.
2025-11-02 17:45:12 +01:00
Matteo Meucci
8e55e6238d
Enhance embedding manipulation testing documentation
...
Expanded testing scenarios for embedding manipulation, including payloads and expected secure behaviors.
2025-11-02 17:28:41 +01:00
Matteo Meucci
ae07885a80
Enhance documentation on embedding manipulation testing
...
Expanded the section on embedding manipulation to include detailed explanations of vulnerabilities, attack vectors, and testing objectives. Updated suggested tools for testing embedding robustness.
2025-11-02 17:23:25 +01:00
Matteo Meucci
c99d2969f3
Refine testing documentation for prompt disclosure
...
Updated sections for clarity and consistency, including test objectives, expected outputs, and suggested tools.
2025-10-30 17:38:58 +01:00
Matteo Meucci
d2b2f3b057
Refine content and headings for agentic behavior testing
...
Updated section headings for consistency and clarity. Revised text for better readability and precision regarding agentic behavior testing.
2025-10-30 17:22:31 +01:00
Matteo Meucci
88f15ccb7d
Revise section titles for clarity in testing guidelines
...
Updated section titles and clarified testing instructions for unsafe outputs.
2025-10-30 17:18:32 +01:00
Matteo Meucci
8bd00636cd
Revise section titles in input leakage testing doc
...
Updated section titles for clarity in testing documentation.
2025-10-30 17:08:58 +01:00
Matteo Meucci
dac1a442f4
Revise test documentation for sensitive data leakage
...
Updated sections for clarity and consistency in testing documentation.
2025-10-30 17:05:34 +01:00
Matteo Meucci
1ca047f15a
Update testing document for indirect prompt injection
2025-10-30 17:03:10 +01:00
Matteo Meucci
8a6445b6ae
Update testing document for prompt injection techniques
2025-10-30 17:01:39 +01:00
Federico Dotta
76ffd748ba
+ Tools vulnerabilities
2025-10-28 09:44:46 +01:00
Federico Dotta
e6cc4ffb64
+ MCP indirect prompt injection
2025-10-28 09:44:33 +01:00
Nicolas Humblot
e637aa06f2
feat: add structured output attack example with source
2025-10-17 11:50:27 +02:00
marti-jorda-roca
6a81e0318c
Add reference to Echo Chamber attack blog
2025-10-16 17:21:47 +02:00
Matteo Meucci
aaffd7e14c
Merge pull request #27 from DotDotSlashRepo/main
...
Enhancements to testcases
2025-10-10 10:40:18 +02:00
Matteo Meucci
c0c38b582e
Merge pull request #32 from zangobot/main
...
Include more testing tools, by dividing them between general-purpouse or domain-specific
2025-09-09 16:37:06 +02:00
