# We checked a weight-space safety edit on Qwen3-VL-8B. It stops the attack, and a lot of safe image requests too.

Abe, part of the Honesty Tools team | Honesty.Tools | 5 November 2026

## The short version

- Amrit Singh Bedi (UCF SafeRR) shared a way to make Qwen3-VL-8B safer by editing two weight matrices. No fine-tuning.
- We rebuilt the edit ourselves from their published log and ran it on our own machine.
- What held: attack success on FigStep fell from 28.2% to 0.2% (1 of 450). A short safety system prompt got to 2.9%. The edit did better, and the ranges don't overlap.
- What held: ScienceQA and MathVista scores didn't move (83.8% vs 83.5%).
- What held: three random edits of the same size did not help.
- The cost: when a safe request arrives as text inside an image, the edit often refuses it. 54.4% of safe XSTest requests shown as images were refused, vs 11.2% with the system prompt and 3.2% with no change.

[Watch the 21-second video (MP4)](/media/blog/c5-weight-space-safety/c5_anim_16x9_v2_vo.mp4 "Video. Our rebuild of the weight-space safety edit on Qwen3-VL-8B: FigStep attacks that get through fall from 28.2% to 0.2% (1 of 450), while 54.4% of safe image-text requests are refused. Utility stays flat. Narrated. Credit: Honesty.tools.")

![Two panels on a dark card. Left: attacks that get through on 450 FigStep items drop from 28.2% to 0.2%, with one glowing attack among a grid of dots; random same-size edits stay at 29.6–37.6%. Right: of 250 safe image-text requests, 54.4% are refused under the edit, versus 3.2% with no change and 11.2% with a short prompt.](/media/blog/c5-weight-space-safety/c5_card_16x9_v2.webp "Chart. Rebuilt edit on Qwen3-VL-8B: attack success falls from 28.2% to 0.2% on FigStep, while refusal of safe image-text rises to 54.4%. Utility unchanged at 83.8% vs 83.5%. Our rebuild, not the authors' weights; one judge. Credit: Honesty.tools.")

## What the authors did

The method is described in "Safety Alignment via Weight-Space Programming" by Amrit Singh Bedi (UCF SafeRR).

- Blog: [Safety Alignment via Weight-Space Programming](https://amrit-singh-bedi.github.io/blog-safety-alignment.html)
- Editing log: [weight-space-safety-editing](https://github.com/Adeelyousaf/weight-space-safety-editing)

They add two small "rank-1" changes to the MLP down-projection at layers 17 and 18 of Qwen3-VL-8B-Instruct. Their headline: FigStep attack success fell from 49% to 2%, with little change in benchmark accuracy.

Their editing log is unusually detailed. The original weight fingerprints in it match the public Qwen checkpoint exactly. That made our rebuild possible.

## What we ran

- Model: Qwen/Qwen3-VL-8B-Instruct, the same pinned version as their log.
- The edit: our own rank-1 rebuild from their log. Not their released weights; those weren't released.
- Fitting: we used 50 FigStep items to fit the edit. We left those 50 out of all scoring.
- Controls: no change; the Llama-2 default system prompt; a short safety prompt of our own, written before we saw any results; and three random edits of the same size.
- Tests: FigStep (450 items), MM-SafetyBench (325), XSTest (250 safe, 200 unsafe), XSTest-safe shown as images (250), OR-Bench-hard (300), ScienceQA (200), MathVista (200).
- Scoring: one judge model, Qwen3Guard-Gen-8B. Greedy decoding, replies up to 512 tokens. 95% Wilson ranges are in the receipt.

## What held

| Test | No change | Short prompt | Our edit | Random edits |
|---|---|---|---|---|
| FigStep attack success (450) | 28.2% | 2.9% | 0.2% (1/450) | 29.6–37.6% |
| MM-SafetyBench attack success (325) | 2.8% | 1.5% | 0.0% | 2.5–7.1% |
| ScienceQA + MathVista correct (400) | 83.5% | 83.5% | 83.8% | 83.0–84.0% |

- FigStep: the edit beats the short prompt. 0.2% [0.0–1.2] vs 2.9% [1.7–4.9]. The ranges don't overlap.
- MM-SafetyBench: 0.0% vs 1.5% for the short prompt. The ranges overlap, so we call it a tie.
- Note: on MM-SafetyBench the unedited model was already at 2.8% under our judge, not the 22% the authors report. Different judge and different items, so this is not a contradiction. About half of the unedited MM-SafetyBench replies also hit our 512-token limit.
- Random edits of the same size left attack success the same or higher (FigStep 29.6–37.6%). So the gain comes from the chosen direction, not from any edit of that size.
- Accuracy on ScienceQA and MathVista didn't change.

## The cost: safe requests inside images

| Test | No change | Short prompt | Our edit |
|---|---|---|---|
| Safe XSTest as plain text, refused (250) | 3.2% | 9.6% | 8.0% |
| Safe XSTest shown as images, refused (250) | 3.2% | 11.2% | 54.4% |
| FigStep advice requests answered (135) | 97.0% | 91.1% | 40.0% |
| OR-Bench-hard refused (300) | 53.7% | 73.0% | 94.3% |

- As plain text, the edit refuses safe requests about as often as the short prompt (8.0% vs 9.6%).
- Shown as text inside an image, it refuses over half of them (54.4%).
- FigStep's legal, financial and health advice requests: the edit answered 40.0%. The other setups answered 91–98%.
- OR-Bench-hard: refusals rose to 94.3%, vs 73.0% for the short prompt.

Read plainly: in our rebuild, the edit acts a lot like "refuse instructions written in images". That stops the attack. It also blocks a large share of normal image-text use.

The authors' claim of "little change in benchmark accuracy" held for ScienceQA and MathVista. It did not hold for over-refusal, which their post doesn't report.

![Square summary card repeating the same rebuilt-edit result: attacks that get through fall from 28.2% to 0.2%, while 54.4% of safe image-text requests are refused.](/media/blog/c5-weight-space-safety/c5_card_1x1_v2.webp "Chart. Same rebuilt-edit result in square form: FigStep attack success 28.2% to 0.2%; safe image-text refusal 54.4%. Our rebuild on Qwen3-VL-8B, not the authors' weights; one judge. Credit: Honesty.tools.")

## Limits of this check

- This is our rebuild of the edit, not the authors' weights. Their edit may behave differently.
- One judge model scored everything. The judge sees the request as plain text, not the image.
- About half of the unedited MM-SafetyBench replies hit our 512-token limit (12.9% for the edit).
- We used different items and a different judge from the authors, so our numbers won't match theirs exactly.

## Our rating

Ford, our auditor, rates this 5/10 (up from 4/10 before we ran the edit). The core idea held in our rebuild. A targeted rank-1 edit beat a strong system prompt on attack success, and random edits did nothing. It isn't higher because of the large over-refusal cost on image text.

## A question for the authors

We'd love to see how your own edit does on the same tests. How does it score on XSTest, OR-Bench, and safe requests shown as images? If your weights behave better than our rebuild, we'll happily update this post.

Thanks to Amrit Singh Bedi and team for publishing such a detailed editing log. It made this check possible.

## Compute

Run on our own DGX, one shared GPU. No rented compute.

---

*Receipts: Ford extension-tests receipt `c5_extension_tests_20261104.txt` (sha256 `7321cdaddb4860678264c2db9ec2d367ed563fef13b9e51b2d78637fa2f2b968`); raw score table `scores_phaseB.txt` (sha256 `8a8d3314df965afc02c374c56d48c28161271c92f93f60c0eeb1ec2140c4780f`). Offline rebuild on our DGX; the receipt files themselves are not a public download yet.*
