Research map / Adversarial robustness and security / Attacks on text and graphs
Revisiting Injective Attacks on Recommender Systems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add diversity-aware objective on top of difficulty-aware objective (ablation) | DADA · ML-100K, WRMF | HR@10: 0.1145 -> 0.1220 | Helped |
| add difficulty-aware objective on top of diversity-aware objective (ablation) | DADA · ML-100K, WRMF | HR@10: 0.1078 -> 0.1220 | Helped |
| add diversity-aware objective on top of difficulty-aware objective (ablation) | DADA · ML-1M, WRMF | HR@50: 0.1217 -> 0.1407 | Helped |
| add both objectives (ablation) | DADA · ML-100K, NCF | HR@10: 0.1405 -> 0.1513 | Helped |
| add both objectives (ablation) | DADA · ML-100K, LightGCN | HR@10: 0.1012 -> 0.1040 | Helped |
| add both objectives (ablation) | DADA · ML-1M, NCF | HR@10: 0.0233 vs 0.0230 (DADA-DICT) | Mixed |
| add diversity-aware objective alone to base (ablation) | DADA · ML-100K, WRMF | HR@10: 0.0901 -> 0.1078 | Helped |
| increase maximum selected items per fake user beyond a suitable value | DADA and baselines · ML-100K and ML-1M, WRMF | HR@50 | Mixed |
| increase fake user budget | DADA and baselines · ML-100K and ML-1M, WRMF | HR@50 | Helped |
Closest papers by meaning
- Trust-GRS: A Trustworthy Training Framework for Graph Neural Network Based Recommender Systems Against Shilling Attacks (AAAI 2025 · similarity 0.84)
- Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game (ICLR 2024 · similarity 0.82)
- User-Creator Feature Polarization in Recommender Systems with Dual Influence (NeurIPS 2024 · similarity 0.81)
- Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation (NeurIPS 2024 · similarity 0.81)
- Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective (AAAI 2025 · similarity 0.81)
- Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design (ICML 2025 · similarity 0.81)
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.