Research map / Adversarial robustness and security / Attacks on text and graphs
Optimizing Personalized Email Filtering Thresholds to Mitigate Sequential Spear Phishing Attacks
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 |
|---|---|---|---|
| model sequential attacker instead of non-sequential attacker when setting thresholds (PEDS vs Laszka et al.) | personalized thresholds · single credential, rho_T > 0 | defender utility | Helped |
| model sequential attacker (PEMS vs Laszka et al.) | personalized thresholds · multiple credentials | defender utility | Helped |
| personalize thresholds instead of uniform threshold | PEDS/PEMS · spear phishing game | defender utility | Helped |
| Laszka et al. personalization vs optimal uniform strategy | Laszka et al. · single credential, rho_T > 0.5 | defender utility | Hurt |
| no spear phishing (rho_T = 0) | PEDS/PEMS vs Laszka et al. · rho_T = 0 | defender utility | No clear effect |
| 10% noise on attack cost estimates (ablation) | PEDS/PEMS · robustness w.r.t. c_u | defender utility | No clear effect |
| 10% noise on susceptibility estimates (ablation) | PEDS/PEMS · robustness w.r.t. a_u | defender utility | No clear effect |
Closest papers by meaning
- Teach LLMs to Phish: Stealing Private Information from Language Models (ICLR 2024 · similarity 0.82)
- 2-in-1 Phishing Detection via Large LM Distillation and Small LM Perturbation (Student Abstract) (AAAI 2025 · similarity 0.81)
- Assessing Per-Sample Membership Inference Vulnerability without Retraining (NeurIPS 2026 · similarity 0.81)
- Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks (AAAI 2024 · similarity 0.81)
- DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans (NeurIPS 2024 · similarity 0.80)
- LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect (NeurIPS 2024 · similarity 0.80)
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.