CryptoAILab/Awesome-LM-SSP

• highreadme#1

  Reposition README H1 and intro to clarify "awesome list" type and "SSP" meaning

  Why:

  CURRENT

  # Awesome-LM-SSP
  
  ## Introduction 
  The resources related to the trustworthiness of large models (LMs) across multiple dimensions (e.g., safety, security, and privacy), with a special focus on multi-modal LMs (e.g., vision-language models and diffusion models).

  COPY-PASTE FIX

  Copy

  # Awesome-LM-SSP: A Curated List of Resources for Large Model Safety, Security, and Privacy
  
  ## Introduction 
  This repository is an **awesome list** of curated resources related to the trustworthiness of large models (LMs) across multiple dimensions (e.g., safety, security, and privacy), with a special focus on multi-modal LMs (e.g., vision-language models and diffusion models). It is a reading list and collection, not a software library or tool. *Note: 'SSP' in the repository name refers to Safety, Security, and Privacy.*

  OpenDoneDismiss
• mediumtopics#2

  Add "reading-list" to repository topics

  Why:

  CURRENT

  adversarial-attacks, awesome-list, diffusion-models, jailbreak, language-model, llm, nlp, privacy, safety, security, vlm

  COPY-PASTE FIX

  Copy

  adversarial-attacks, awesome-list, diffusion-models, jailbreak, language-model, llm, nlp, privacy, reading-list, safety, security, vlm

  OpenDoneDismiss
• lowreadme#3

  Add a "Keywords / Tags" section to the README

  Why:

  COPY-PASTE FIX

  Copy

  ## Keywords / Tags
  
  Awesome List, Reading List, LLM Safety, LLM Security, LLM Privacy, Large Model Trustworthiness, Adversarial Attacks on LLMs, Jailbreaking LLMs, Vision-Language Model Security, Diffusion Model Safety, AI Ethics, Responsible AI Research.

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  Where can I find resources on securing large language models against adversarial attacks?

  you: not recommended
  AI recommended (in order):

  1. Adversarial Robustness Toolbox (ART) (IBM/adversarial-robustness-toolbox)
  2. Microsoft Counterfit (Azure/counterfit)
  3. Garak (lacuna-ai/garak)
  4. Hugging Face's `transformers` library (huggingface/transformers)

  AI recommended 4 alternatives but never named CryptoAILab/Awesome-LM-SSP. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  What are the best practices for ensuring privacy and safety in large AI models?

  you: not recommended
  AI recommended (in order):

  1. TensorFlow Privacy
  2. PySyft
  3. SmartNoise
  4. TensorFlow Federated
  5. PySyft
  6. Flower
  7. Microsoft SEAL
  8. OpenFHE
  9. PyTorch-HE
  10. PySyft
  11. MP-SPDZ
  12. FRESCO
  13. Privitar
  14. Informatica Data Masking
  15. IBM Adversarial Robustness Toolbox
  16. CleverHans
  17. LIME
  18. SHAP
  19. Google's What-If Tool
  20. InterpretML

  AI recommended 20 alternatives but never named CryptoAILab/Awesome-LM-SSP. This is the gap to close.

  Show full AI answer

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of CryptoAILab/Awesome-LM-SSP?

  pass
  ⚠AI did not name CryptoAILab/Awesome-LM-SSP — likely talking about a different project

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts CryptoAILab/Awesome-LM-SSP in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named CryptoAILab/Awesome-LM-SSP explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo CryptoAILab/Awesome-LM-SSP solve, and who is the primary audience?

  pass
  ⚠AI did not name CryptoAILab/Awesome-LM-SSP — likely talking about a different project

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?