Research map / Adversarial robustness and security / Certified and empirical robustness
RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
Zhuoqun Huang, Neil G Marchant, Keane Lucas, Lujo Bauer, Olga Ohrimenko, Benjamin I. P. Rubinstein
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use randomized deletion smoothing (RS-Del) instead of randomized ablation (RS-Abn) with equal smoothing parameters | MalConv malware detector · Sleipnir2 / VTFeed | certified accuracy | Improved |
| smooth MalConv with RS-Del at p_del=99.5% versus non-smoothed model | MalConv · Sleipnir2 | clean accuracy: 2-3% drop | Hurt |
| vary decision threshold eta at p_del=99.5% (ablation) | RS-Del · Sleipnir2 | median certified radius for malicious class: up to 582 bytes | Improved |
| apply RS-Del smoothing instead of non-smoothed baseline against Disp attack | MalConv · Sleipnir2 / VTFeed | attack success rate: 20 percentage point decrease | Improved |
| apply RS-Del smoothing against six published attacks | MalConv · Sleipnir2 / VTFeed | attack success rate | Mixed |
| increase deletion probability p_del (ablation) | RS-Del · Sleipnir2 | clean accuracy vs certified radius | Mixed |
Closest papers by meaning
- AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness (NeurIPS 2025 · similarity 0.88)
- DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness (ICLR 2024 · similarity 0.86)
- Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing (ICML 2024 · similarity 0.85)
- Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models (NeurIPS 2024 · similarity 0.85)
- Average Certified Radius is a Poor Metric for Randomized Smoothing (ICML 2025 · similarity 0.85)
- Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
