Sniffer: A Novel Model Type Detection System against Machine-Learning-as-a-Service Platforms
Summary: Sniffer detects the underlying model class of black-box MLaaS APIs via a Probe (with Generator and Querier) using novel algorithms, enabling selection of model-type-aware attack strategies. It chooses optimal attacks from an Arsenal and demonstrates interactive exploitation against five mainstream MLaaS platforms. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhuo Ma
- 2. Yilong Yang
- 3. Bin Xiao
- 4. Yang Liu
- 5. Xinjing Liu
- 6. Zhuoran Ma
- 7. Tong Yang
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,331 | A Demonstration of Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference | 2020 | VLDB | 7.2131599e-05 |
| 3,407 | End-to-end Optimization of Machine Learning Prediction Queries | 2022 | SIGMOD | 7.1295646e-05 |
Previous
Page 1 / 1
Next