[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
active 2024-03-07 → 2026-03-12 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 736 days from 2024-03-07 to 2026-03-12. Pushes: 4 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 14 total, peak 3 in a day. Comments: 30 total, peak 12 in a day. Stars: 36 total, peak 2 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| boyiwei | 28 | 4 | 0 | 16 |
| zzxxxl | 8 | 0 | 0 | 7 |
| jeffreyzhanghc | 4 | 0 | 0 | 4 |
| ybwang119 | 2 | 0 | 0 | 1 |
| YichenBC | 1 | 0 | 0 | 1 |
| MqLeet | 1 | 0 | 0 | 1 |
| Zongmin741 | 1 | 0 | 0 | 0 |
| orgadhadas | 1 | 0 | 0 | 0 |
| SJSoJSooJ | 1 | 0 | 0 | 0 |
| slardar94 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#16Zongmin7412026-03-12 00:47Code to calculate "Rank-level subspace similarity" for Fig. 4b
- Issue comment#12boyiwei2025-03-30 12:43In prune_wandg_set_difference, there is No such file or directory
- Issue#12boyiwei2025-03-30 12:43In prune_wandg_set_difference, there is No such file or directory
- Issue#12SJSoJSooJ2025-03-30 09:27In prune_wandg_set_difference, there is No such file or directory
- Issue comment#4boyiwei2025-03-14 07:48Great work. Can you release the code fine-tuning the models while the alignment region is frozen?
- Issue comment#11boyiwei2025-02-23 21:27Why did you take the absolute value in the SNIP score?
- Issue#11boyiwei2025-02-23 21:27Why did you take the absolute value in the SNIP score?
- Issue#11orgadhadas2025-02-23 15:31Why did you take the absolute value in the SNIP score?
- Issue comment#10MqLeet2025-02-19 02:28Code about drawing Fig.4 in paper
- Issue#8boyiwei2025-01-18 22:04Clarification on the loop for wandg
- Issue comment#9boyiwei2025-01-02 14:08error in zero-shot evaluation for safety-related ranks
- Issue comment#9ybwang1192025-01-02 12:26error in zero-shot evaluation for safety-related ranks
- Issue#9ybwang1192025-01-02 12:22error in zero-shot evaluation for safety-related ranks
- Issue#5boyiwei2024-09-10 15:29Perplexity is way off for Llama2 models
- Issue comment#5boyiwei2024-09-09 01:59Perplexity is way off for Llama2 models
- Issue#5slardar942024-09-08 02:05Perplexity is way off for Llama2 models
- Issue comment#2jeffreyzhanghc2024-08-28 03:30set_difference problem
- Issue comment#2boyiwei2024-08-28 03:12set_difference problem
- Issue comment#2jeffreyzhanghc2024-08-28 03:08set_difference problem
- Issue comment#2boyiwei2024-08-28 02:59set_difference problem
- Issue comment#2jeffreyzhanghc2024-08-28 02:56set_difference problem
- Issue comment#2boyiwei2024-08-28 02:47set_difference problem
- Issue comment#2jeffreyzhanghc2024-08-28 02:45set_difference problem
- Issue#4boyiwei2024-07-20 08:15Great work. Can you release the code fine-tuning the models while the alignment region is frozen?
- Issue comment#4YichenBC2024-07-20 07:59Great work. Can you release the code fine-tuning the models while the alignment region is frozen?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 36 stars here means stars gained during the window, not the repo's star count.