Browse AI risks

5 entries

1. 02.01.03 · Risk Sub-Category

   Harmful Content

   Privacy Leakage

   "Privacy Leakage means the generated content includes sensitive personal information"

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 2 2.1 AI Unintentional Post-deployment

2. 02.07.00 · Risk Category

   Privacy Leakage

   "The model is trained with personal data in the corpus and unintentionally exposing them during the conversation."

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 2 2.1 AI Unintentional Other

3. 02.07.01 · Risk Sub-Category

   Privacy Leakage

   Private Training Data

   "As recent LLMs continue to incorporate licensed, created, and publicly available data sources in their corpora, the potential to mix private data in the training corpora is significantly increased. The misused private data, also named as personally identifiable information (PII) [84], [86], could contain various types of sensitive data subjects, including an individual person’s name, email, phone number, address, education, and career. Generally, injecting PII into LLMs mainly occurs in two settings — the exploitation of web-collection data and the alignment with personal humanmachine convers

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 2 2.1 Human Unintentional Pre-deployment

4. 02.07.02 · Risk Sub-Category

   Privacy Leakage

   Memorization in LLMs

   "Memorization in LLMs refers to the capability to recover the training data with contextual prefixes. According to [88]–[90], given a PII entity x, which is memorized by a model F. Using a prompt p could force the model F to produce the entity x, where p and x exist in the training data. For instance, if the string “Have a good day!\n [email protected]” is present in the training data, then the LLM could accurately predict Alice’s email when given the prompt “Have a good day!\n”."

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 2 2.1 AI Unintentional Pre-deployment

5. 02.07.03 · Risk Sub-Category

   Privacy Leakage

   Association in LLMs

   "Association in LLMs refers to the capability to associate various pieces of information related to a person. According to [68], [86], given a pair of PII entities (xi , xj ), which is associated by a model F. Using a prompt p could force the model F to produce the entity xj , where p is the prompt related to the entity xi . For instance, an LLM could accurately output the answer when given the prompt “The email address of Alice is”, if the LLM associates Alice with her email “[email protected]”. L"

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 2 2.1 AI Unintentional Pre-deployment

Disclaimer: informational only, not legal advice. Verify every claim against the linked official sources and consult a qualified lawyer before acting.