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

..

AITG-APP-01_Testing_for_Prompt_Injection.md

1. Specified that temperature=0 does not imply reproducibility (https://arxiv.org/pdf/2506.09501)

2025-07-25 20:26:32 +02:00

AITG-APP-02_Testing_for_Indirect_Prompt_Injection.md

Add EchoLeak technique to indirect prompt injection testing

2025-06-25 23:39:39 -05:00

AITG-APP-03_Testing_for_Sensitive_Data_Leak.md

fixing typos in multiple texts.

2025-06-29 13:48:42 +02:00

AITG-APP-04_Testing_for_Input_Leakage.md

fix: correct spelling errors in test documentation files

2025-06-25 11:59:29 -05:00

AITG-APP-05_Testing_for_Unsafe_Outputs.md

The unsafe output test now includes hate releated unsafe content as part of the tests.

2025-07-17 15:14:33 +02:00

AITG-APP-06_Testing_for_Agentic_Behavior_Limits.md

Add direct tool invocation sections

2025-06-26 16:42:37 +02:00

AITG-APP-07_Testing_for_Prompt_Disclosure.md

Add prompt disclosure techniques

2025-06-26 16:42:50 +02:00

AITG-APP-08_Testing_for_Embedding_Manipulation.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-APP-09_Testing_for_Model_Extraction.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-APP-10_Testing_for_Content_Bias.md

1. Specified that temperature=0 does not imply reproducibility (https://arxiv.org/pdf/2506.09501)

2025-07-25 20:26:32 +02:00

AITG-APP-11_Testing_for_Hallucinations.md

fixing typos in multiple texts.

2025-06-29 13:48:42 +02:00

AITG-APP-12_Testing_for_Toxic_Output.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-APP-13_Testing_for_Over-Reliance_on_AI.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-APP-14_Testing_for_Explainability_and_Interpretability.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-DAT-01_Testing_for_Training_Data_Exposure.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-DAT-02_Testing_for_Runtime_Exfiltration.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-DAT-03_Testing_for_Dataset_Diversity_and_Coverage.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-DAT-04_Testing_for_Harmful_Content_in_Data.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-DAT-05_Testing_for_Data_Minimization_and_Consent.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-INF-01_Testing_for_Supply_Chain_Tampering.md

fix: correct spelling errors in test documentation files

2025-06-25 11:59:29 -05:00

AITG-INF-02_Testing_for_Resource_Exhaustion.md

fixing typos in multiple texts.

2025-06-29 13:48:42 +02:00

AITG-INF-03_Testing_for_Plugin_Boundary_Violations.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-INF-04_Testing_for_Capability_Misuse.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-INF-05_Testing_for_Fine-tuning_Poisoning.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-INF-06_Testing_for_Dev-Time_Model_Theft.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-MOD-01_Testing_for_Evasion_Attacks.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-MOD-02_Testing_for_Runtime_Model_Poisoning.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-MOD-03_Testing_for_Poisoned_Training_Sets.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-MOD-04_Testing_for_Membership_Inference.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-MOD-05_Testing_for_Inversion_Attacks.md

fixing typos in multiple texts.

2025-06-29 13:48:42 +02:00

AITG-MOD-06_Testing_for_Robustness_to_New_Data.md

Add files via upload

2025-06-17 21:30:54 +02:00

AITG-MOD-07_Testing_for_Goal_Alignment.md

Add files via upload

2025-06-17 21:30:54 +02:00