Research map / Adversarial robustness and security / Attacks on text and graphs
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks
Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Guha Thakurta
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 |
|---|---|---|---|
| Give the attacker access to the clean training set before crafting poison examples | LASSO feature selection · Gaussian feature selection | probability of changing selected feature support: at most ε1 vs. at least ε2 | Improved |
| Increase the fraction of the training data visible to the attacker | LASSO feature-selection poisoning · Gaussian synthetic data | number of poison points needed to add a feature | Improved |
| Increase the fraction of the training data visible to the attacker | LASSO feature-selection poisoning · SMK and TOX | number of poison points needed to add a feature | Mixed |
| Increase the fraction of the training data visible to the attacker | LASSO feature-selection poisoning · MNIST | number of poison points needed to add a feature | Improved |
| Use a data-aware attack that targets a rotated halfspace selected using the training set | ERM · Gaussian halfspace classification | test error | Hurt |
| Use the tested oblivious poisoning strategies instead of selecting poison examples from the training set | ERM · Gaussian halfspace classification | test error | No clear effect |
Closest papers by meaning
- On Robustness of Linear Classifiers to Targeted Data Poisoning (AAAI 2026 · similarity 0.89)
- What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners? (NeurIPS 2023 · similarity 0.89)
- Not All Poisons are Created Equal: Robust Training against Data Poisoning (ICML 2022 · similarity 0.89)
- Lethal Dose Conjecture on Data Poisoning (NeurIPS 2022 · similarity 0.89)
- Model-Targeted Poisoning Attacks with Provable Convergence (ICML 2021 · similarity 0.88)
- Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness (NeurIPS 2025 · similarity 0.86)
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.
