Matteo Meucci
066bfaa2dd
Merge pull request #25 from fedric95/main
2025-07-26 00:17:36 +04:00
fedric95
d27026fda7
Merge branch 'OWASP:main' into main
2025-07-25 20:30:56 +02:00
Federico Ricciuti
0dd87354da
1. Specified that temperature=0 does not imply reproducibility ( https://arxiv.org/pdf/2506.09501 )
...
2. Pointed out that LLMs are generally less secure in low-resource languages
3. Made some order on the payloads for the bias test, now it using always the same base example.
2025-07-25 20:26:32 +02:00
Matteo Meucci
124c92f538
Merge pull request #24 from federicodotta/main
2025-07-25 14:55:11 +04:00
federicodotta
897c532bba
+ Planning instructions to avoid issues with token consumption
2025-07-25 12:18:11 +02:00
Matteo Meucci
dfee7656c2
Merge pull request #23 from fedric95/main
2025-07-17 18:26:58 +04:00
Federico Ricciuti
9da16a16c1
Correction of the readme to refer to the correct changed test
2025-07-17 15:22:07 +02:00
Federico Ricciuti
977235af4d
Introduction of the AITG-APP-10_Testing_for_Content_Bias.md, with tests to detect biased decisions made by the AI System.
2025-07-17 15:16:22 +02:00
Federico Ricciuti
49ee4b9d6c
The unsafe output test now includes hate releated unsafe content as part of the tests.
...
AITG-APP-10_Testing_for_Harmful_Content_Bias.md replaced with AITG-APP-10_Testing_for_Content_Bias.md, and now it focuses on the detection of biases contened in the generated outputs.
2025-07-17 15:14:33 +02:00
Matteo Meucci
11e22f40cd
Merge pull request #22 from federicodotta/main
2025-07-14 11:09:32 +04:00
federicodotta
82b7a18ef4
README updated
2025-07-14 08:19:58 +02:00
Matteo Meucci
db71d7c1a4
Merge pull request #21 from federicodotta/main
2025-07-13 13:52:59 +04:00
federicodotta
2b16a5c5f3
+ Testing Limitations and Requirements
2025-07-13 11:21:09 +02:00
Matteo Meucci
71b4f26900
Merge pull request #20 from fedric95/main
2025-07-12 21:30:58 +04:00
Federico Ricciuti
198167aebe
- Introduced the necessity of defining a safety taxonomy before conducting the tests: the definition of what is safe and what is unsafe depends on the application.
...
- Linked an existing safety taxonomy
- Added examples of moderation models
- Removed most of the references to the concept of bias. They should be addressed in another test.
TO-DO
- Include tests that consider the potential multimodal nature of the application (right now it is more text-only)
- Make a specific test to evaluate the biases of the AI application under test and remove all the references to biases in this test
2025-07-12 19:12:00 +02:00
Matteo Meucci
f4a5804a70
Merge pull request #19 from federicodotta/main
2025-07-12 16:42:53 +04:00
federicodotta
5dbedf3dc3
Prompt Injection Techniques section addeded
2025-07-12 13:51:10 +02:00
federicodotta
5a434e776b
Update in typo tricks
2025-07-12 12:35:05 +02:00
federicodotta
a56ba3f4e6
+ Echo Chamber Attack
2025-07-12 12:24:58 +02:00
federicodotta
b483d240cf
+ AntiGPT reference
2025-07-12 11:53:03 +02:00
federicodotta
abfcbde568
+ AntiGPT Prompt Injection
2025-07-12 11:49:27 +02:00
Matteo Meucci
a6b1ed20fe
Merge pull request #18 from mmorana1/patch-8
...
Update 2.1_Identify_AI_Threats.md
2025-07-09 20:11:59 +04:00
Marco Morana
250ead1ffc
Update 2.1_Identify_AI_Threats.md
...
Re-aligned all references and links
2025-07-09 11:38:48 -04:00
Matteo Meucci
d452ac3a95
Merge pull request #17 from mmorana1/patch-7
...
Update 2.1_Identify_AI_Threats.md
2025-07-09 18:34:53 +04:00
Marco Morana
f821459f13
Update 2.1_Identify_AI_Threats.md
...
Reference more specialized taxonomies like the one developed by Pangea
2025-07-09 10:18:43 -04:00
Matteo Meucci
13315f501a
Merge pull request #16 from mmorana1/patch-6
...
Update References.md
2025-07-09 18:08:20 +04:00
Marco Morana
5fef43e31f
Update References.md
...
Added ref [23] to PJI taxonomy
2025-07-09 09:55:52 -04:00
Matteo Meucci
9ceb54ed27
Merge pull request #15 from mmorana1/patch-5
2025-07-09 10:37:59 +04:00
Marco Morana
2c6a41ef75
Update 2.1_Identify_AI_Threats.md
...
Add note on risk
2025-07-08 18:17:12 -04:00
Matteo Meucci
8175757126
Merge pull request #13 from mmorana1/patch-2
2025-07-08 22:36:47 +04:00
Marco Morana
c17d9cdf46
Update README.md
...
Cosmetic changes
2025-07-01 14:59:33 -04:00
Matteo Meucci
aa34513214
Merge pull request #12 from mmorana1/patch-2
...
Update README.md
2025-07-01 20:26:40 +02:00
Marco Morana
def23545ab
Update README.md
...
Added references to CSA Red Teaming guide and OWASP AI VSS
2025-07-01 14:16:04 -04:00
Matteo Meucci
4e44d02705
Merge pull request #11 from mmorana1/patch-1
...
Testing small edits
2025-06-30 22:52:26 +02:00
Marco Morana
84c9c7c989
Testing small edits
2025-06-30 15:36:22 -04:00
Matteo Meucci
d7acc33f62
Merge pull request #10 from didier-durand/fix-typos
...
fixing typos in multiple texts.
2025-06-29 15:32:17 +02:00
Didier Durand
e754867dd5
fixing typos in multiple texts.
2025-06-29 13:48:42 +02:00
Matteo Meucci
fd20d35e01
Merge pull request #9 from GraoMelo/patch-1
...
Update 2.2_Appendix_B.md
2025-06-26 20:16:11 +02:00
GraoMelo
b03267133e
Update 2.2_Appendix_B.md
...
fixed #8
2025-06-26 15:12:53 -03:00
Matteo Meucci
451a558764
Merge pull request #6 from federicodotta/main
...
Updates to AITG-APP-01, AITG-APP-03, AITG-APP-05, AITG-APP-06, AITG-APP-07 and AITG-INF-02
2025-06-26 19:27:44 +02:00
federicodotta
a50c0ceb65
Fix copy/paste error in AITG-INF-02
2025-06-26 18:36:36 +02:00
federicodotta
d390fa1605
Add some attack vectors and some additional notes to AITG-INF-02
2025-06-26 18:29:32 +02:00
federicodotta
77ebe9e3b5
Add prompt disclosure techniques
2025-06-26 16:42:50 +02:00
federicodotta
15218fd5cb
Add direct tool invocation sections
2025-06-26 16:42:37 +02:00
federicodotta
29c2bcfeca
Add XSS attack vectors
2025-06-26 16:42:21 +02:00
federicodotta
249ab5fb84
Add some data leaks related to tool list and reasoning
2025-06-26 16:42:11 +02:00
federicodotta
25fc713549
Added some prompt injection techniques
2025-06-26 16:41:44 +02:00
Matteo Meucci
81d37dc81a
Merge pull request #5 from SitaRamSai/add-echoleak-technique
...
Add EchoLeak technique to indirect prompt injection testing
2025-06-26 09:43:02 +02:00
Ram K
0a93f78ebd
Add EchoLeak technique to indirect prompt injection testing
...
- Added Reference-Style Markdown Injection (EchoLeak Technique) section
- Included real-world example with CVE-2025-32711 from Aim Security Labs
- Enhanced testing methodology for markdown-based data exfiltration attacks
2025-06-25 23:39:39 -05:00
Matteo Meucci
6e9a792284
Merge pull request #4 from jsredmond/docs/more-spelling-fixes
...
docs: fix README spacing, prompt-injection typos
2025-06-25 23:00:36 +02:00
