Backdoor attacks against Machine Learning IRL
Comments on “Backdoor attacks against Machine Learning IRL”
Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked
In Phrack, G. Cherubin describes a parser flaw in ONNX Runtime: sparse tensors are densified at load time, before external-path validation, so a model file can make the runtime read arbitrary files or memory addresses. Combined with graph logic in a Qwen2.5-7B-Instruct model, a trigger word makes the model emit the read bytes as tokens, with no change to the runtime. Both fixes shipped in onnxruntime v1.27.0. The author's point for builders: downloaded models are code and need the same vetting as libraries.
Why it ranked
No. 3 of 144 with a score of 0.77. The panel rated it highest on technical depth (0.96) and substantiated (0.89), lowest on audience breadth (0.71).
- AI judgeJudge 2claude-haiku-5-5
- Detailed, well-evidenced ML supply-chain exploit: an ORT parser flaw enabling arbitrary file read and a deterministic LLM backdoor for exfiltration, with disclosure timeline. Highly relevant to security and AI builders.
- AI judgeJudge 3gpt-5.6-luna
- A technically detailed, code-backed disclosure demonstrates deterministic arbitrary file/memory reads and data exfiltration through malicious ONNX graphs, with reproducible mechanics, patches, and a clear security lesson for AI deployment.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.77total under rubric v2.3
- Significance0.72
- Reader interest0.86
- Audience breadth0.71
- Practical relevance0.78
- Substantiated0.89
- Technical depth0.96
- New information0.88
- Counts against: Promotional0.03
- Counts against: Overclaim0.18
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.71 | 0.60 | 0.85 | 0.72 | 0.25 | +0.24 | +0.173 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.78 | 0.85 | 0.95 | 0.86 | 0.17 | +0.26 | +0.224 |
| Audience breadthHow many people who build technology does it concern? | 0.74 | 0.67 | 0.72 | 0.71 | 0.07 | +0.13 | +0.092 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.76 | 0.70 | 0.88 | 0.78 | 0.18 | +0.22 | +0.172 |
| SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations. | 0.90 | 0.85 | 0.92 | 0.89 | 0.07 | +0.05 | +0.045 |
| Technical depthHow technically substantive is it? | 0.99 | 0.90 | 0.98 | 0.96 | 0.09 | +0.05 | +0.048 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.85 | 0.85 | 0.93 | 0.88 | 0.08 | +0.05 | +0.044 |
| PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional. | 0.05 | 0.03 | 0.02 | 0.03 | 0.03 | −0.19 | −0.006 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.28 | 0.15 | 0.12 | 0.18 | 0.16 | −0.11 | −0.020 |
| Sum of contributions | +0.770 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.770 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-11-19/3/"><img src="https://rubric.hrih.si/badge/2026-11-19/3.svg" alt="Ranked #3 on Rubric, 19 Nov 2026" width="238" height="28"></a>Claim check
Claim check: no checkable claims. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.
No checkable claims were extracted from this story.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 19 Nov 2026, 05:47 UTC. It played no part in the ranking.