Comparison
LLMs-Finetuning-Safety vs CipherChat
Verdict
Pick LLMs-Finetuning-Safety if lLMs-Finetuning-Safety demonstrates the safety risks associated with fine-tuning GPT-3.5 Turbo using few adversarially designed examples; pick CipherChat if assess LLM safety alignment on non-natural texts like ciphers.
Markdown twin · LLMs-Finetuning-Safety alternatives · CipherChat alternatives
GraphCanon updated Oct 5, 2026
18views this month
vs
Trust & integrity
| Signal | LLMs-Finetuning-Safety | CipherChat |
|---|---|---|
| Maintenance | Dormant (954d since push) As of Oct 5, 2026 · github_public_v1 | Slowing (361d since push) As of Oct 5, 2026 · github_public_v1 |
| Provenance | Not a fork · Personal account As of Oct 5, 2026 · github_public_v1 | Not a fork · Organization account As of Oct 5, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- LLMs-Finetuning-Safety
- Demonstrates safety risks in fine-tuning GPT-3.5 Turbo with adversarial examples
- CipherChat
- A framework to assess safety alignment generalization in LLMs for non-natural languages
Stars
- LLMs-Finetuning-Safety
- 359
- CipherChat
- 631
Forks
- LLMs-Finetuning-Safety
- 39
- CipherChat
- 67
Open issues
- LLMs-Finetuning-Safety
- 3
- CipherChat
- 0
Language
- LLMs-Finetuning-Safety
- Python
- CipherChat
- Python
Adopt for
- LLMs-Finetuning-Safety
- LLMs-Finetuning-Safety demonstrates the safety risks associated with fine-tuning GPT-3.5 Turbo using few adversarially designed examples.
- CipherChat
- Assess LLM safety alignment on non-natural texts like ciphers.
Persona
- LLMs-Finetuning-Safety
- -
- CipherChat
- -
Runtime
- LLMs-Finetuning-Safety
- -
- CipherChat
- -
License
- LLMs-Finetuning-Safety
- MIT
- CipherChat
- MIT
Last pushed
- LLMs-Finetuning-Safety
- Feb 23, 2024
- CipherChat
- Oct 9, 2025
Categories
- LLMs-Finetuning-Safety
- Evaluation & Observability, Model Training
- CipherChat
- Evaluation & Observability, Model Training
Trust and health
Maintenance
- LLMs-Finetuning-Safety
- Dormant (18%)
- CipherChat
- Slowing (36%)
Days since push
- LLMs-Finetuning-Safety
- 954d
- CipherChat
- 361d
Open issues (now)
- LLMs-Finetuning-Safety
- 3
- CipherChat
- 0
Stars delta
- LLMs-Finetuning-Safety
- +1 (30d)
- CipherChat
- +3 (30d)
Owner type
- LLMs-Finetuning-Safety
- User
- CipherChat
- Organization
Full report
- LLMs-Finetuning-Safety
- Trust report
- CipherChat
- Trust report
Choose LLMs-Finetuning-Safety if…
- Pricing: Open-source under the MIT license; free to use and modify. OpenAI API usage cost applies, but this repository demonstrates effects at less than $0.20..
- Tags unique to LLMs-Finetuning-Safety: adversarial training, llm, llm-finetuning, model safety.
- When evaluating the risk of compromised safety in language models after fine-tuning them on small, carefully crafted datasets.
When NOT to use LLMs-Finetuning-Safety
- When generalizing safety risks to other large language models that have different underlying architectures or safeguard mechanisms than GPT-3.5 Turbo.
- If intending to use this tool as a method of fine-tuning any model for enhancing its performance on specific tasks, given it is designed for illustrating risk rather than improving capabilities.
Choose CipherChat if…
- Tags unique to CipherChat: cipher analysis, llm-evaluation, safety alignment.
- Need to evaluate how well an LLM's safety aligns when processing encrypted or encoded inputs
- More GitHub stars (631 vs 359) - visibility, not fit.
When NOT to use CipherChat
- Looking for direct interaction with natural human language without encryption needs
- Seeking tools that focus on typical text analysis for common languages like English, Spanish
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (LLM-Tuning-Safety/LLMs-Finetuning-Safety) · observed Oct 5, 2026
- GitHub forks (LLM-Tuning-Safety/LLMs-Finetuning-Safety) · observed Oct 5, 2026
- Last push (LLM-Tuning-Safety/LLMs-Finetuning-Safety) · observed Feb 23, 2024
- License file (MIT) · observed Oct 5, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (RobustNLP/CipherChat) · observed Oct 5, 2026
- GitHub forks (RobustNLP/CipherChat) · observed Oct 5, 2026
- Last push (RobustNLP/CipherChat) · observed Oct 9, 2025
- License file (MIT) · observed Oct 5, 2026
- Decision facts (enrichment) · observed Jul 16, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
GitHub stars on cards: LLMs-Finetuning-Safety 359 · CipherChat 631 (synced Oct 5, 2026).
Common questions
- What is the difference between LLMs-Finetuning-Safety and CipherChat?
- LLMs-Finetuning-Safety: Demonstrates safety risks in fine-tuning GPT-3.5 Turbo with adversarial examples. CipherChat: A framework to assess safety alignment generalization in LLMs for non-natural languages. See the comparison table for live GitHub stats and shared categories.
- When should I choose LLMs-Finetuning-Safety over CipherChat?
- Choose LLMs-Finetuning-Safety over CipherChat when Pricing: Open-source under the MIT license; free to use and modify. OpenAI API usage cost applies, but this repository demonstrates effects at less than $0.20.; Tags unique to LLMs-Finetuning-Safety: adversarial training, llm, llm-finetuning, model safety; When evaluating the risk of compromised safety in language models after fine-tuning them on small, carefully crafted datasets.
- When should I choose CipherChat over LLMs-Finetuning-Safety?
- Choose CipherChat over LLMs-Finetuning-Safety when Tags unique to CipherChat: cipher analysis, llm-evaluation, safety alignment; Need to evaluate how well an LLM's safety aligns when processing encrypted or encoded inputs; More GitHub stars (631 vs 359) - visibility, not fit.
- When should I avoid LLMs-Finetuning-Safety?
- When generalizing safety risks to other large language models that have different underlying architectures or safeguard mechanisms than GPT-3.5 Turbo. If intending to use this tool as a method of fine-tuning any model for enhancing its performance on specific tasks, given it is designed for illustrating risk rather than improving capabilities.
- When should I avoid CipherChat?
- Looking for direct interaction with natural human language without encryption needs Seeking tools that focus on typical text analysis for common languages like English, Spanish
- Is LLMs-Finetuning-Safety or CipherChat more popular on GitHub?
- CipherChat has more GitHub stars (631 vs 359). Stars measure visibility, not whether either tool fits your constraints.
- Are LLMs-Finetuning-Safety and CipherChat open source?
- Yes - both are open-source projects on GitHub (LLMs-Finetuning-Safety: MIT, CipherChat: MIT).
- Where can I find alternatives to LLMs-Finetuning-Safety or CipherChat?
- GraphCanon lists graph-backed alternatives at LLMs-Finetuning-Safety alternatives and CipherChat alternatives (LLMs-Finetuning-Safety markdown twin, CipherChat markdown twin), ranked by typed relationship edges rather than popularity votes.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
- Which is better maintained, LLMs-Finetuning-Safety or CipherChat?
- LLMs-Finetuning-Safety: Dormant. CipherChat: Slowing. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
- Where are the full trust reports for LLMs-Finetuning-Safety and CipherChat?
- GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: LLMs-Finetuning-Safety trust report; CipherChat trust report.