SA-ADP: Sensitivity-Aware Adaptive Differential Privacy for Large Language Models

Documenti analoghi

• Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems
  di: ElShehaby, Mohamed, et al.
  Pubblicazione: (2025)
• A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
  di: elShehaby, Mohamed, et al.
  Pubblicazione: (2026)
• Introducing Adaptive Continuous Adversarial Training (ACAT) to Enhance ML Robustness
  di: elShehaby, Mohamed, et al.
  Pubblicazione: (2024)
• A Novel Perturb-ability Score to Mitigate Evasion Adversarial Attacks on Flow-Based ML-NIDS
  di: elShehaby, Mohamed, et al.
  Pubblicazione: (2024)
• Evasion Adversarial Attacks Remain Impractical Against ML-based Network Intrusion Detection Systems, Especially Dynamic Ones
  di: elShehaby, Mohamed, et al.
  Pubblicazione: (2023)