# CryptoAILab/Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Repository: https://github.com/CryptoAILab/Awesome-LM-SSP
Canonical: https://ross.abutalabs.com/products/awesome-lm-ssp
Homepage: https://github.com/CryptoAILab/Awesome-LM-SSP
License: Apache-2.0
License Family: permissive
Topics: adversarial-attacks, awesome-list, diffusion-models, jailbreak, language-model, llm, nlp, privacy, safety, security, vlm
Last push: 2026-06-17T01:49:19+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 35, longevity 69
- inputs: {"age_days": 967, "days_push": 78, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2066, forks 164 (observed 2026-08-28T04:06:10.136159+00:00)

## What it is
A curated awesome-list reading list of papers, surveys, toolkits, benchmarks, and competitions on the safety, security, and privacy of large models, with special focus on multi-modal LMs like vision-language and diffusion models. It contains over 2,300 manually collected papers organized into categories such as jailbreak attacks and defenses.

## Use cases
- find papers on llm jailbreak attacks
- research on large language model safety
- survey of adversarial attacks on vision-language models
- reading list for llm security and privacy
- find benchmarks for evaluating llm trustworthiness
- literature review on diffusion model safety
- keep up with new research on ai model privacy

## When to choose
- you need a comprehensive, actively maintained bibliography of LLM safety/security/privacy research
- you want papers organized by model type (LLM, VLM, SLM, diffusion) and topic with venue metadata
- you are starting research on jailbreaks, adversarial attacks, or model trustworthiness

## When to avoid
- you need runnable software or a security toolkit rather than a paper list
- you want automated, exhaustive coverage rather than manually curated selections
- you need production security tooling for deploying LLMs

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, privacy, nlp
- domain: large-language-models, security, artificial-intelligence, awesome-lists
- platform: cross-platform
- tags: awesome-list, llm-safety, llm-security, jailbreak, adversarial-attacks, reading-list, vision-language-models, diffusion-models, trustworthiness, papers, natural-language-processing

## Member repositories
- CryptoAILab/Awesome-LM-SSP (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:10.136159+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:56:53.366852+00:00, confidence not recorded.
  - readme: https://github.com/CryptoAILab/Awesome-LM-SSP (fetched 2026-08-28T04:06:10.136159+00:00, sha 11e310d4680f)
  - homepage: https://github.com/CryptoAILab/Awesome-LM-SSP (fetched 2026-08-29T10:37:36.175420+00:00, sha fb7387314fed)
- Data as of 2026-08-30T08:39:29.467469+00:00.