Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor

Documenti analoghi

• Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study
  di: Chai, Duo, et al.
  Pubblicazione: (2025)
• PVF (Parameter Vulnerability Factor): A Scalable Metric for Understanding AI Vulnerability Against SDCs in Model Parameters
  di: Jiao, Xun, et al.
  Pubblicazione: (2024)
• Spatial Variation-Aware Read Disturbance Defenses: Experimental Analysis of Real DRAM Chips and Implications on Future Solutions
  di: Yağlıkçı, Abdullah Giray, et al.
  Pubblicazione: (2024)
• Understanding and Mitigating Covert Channel and Side Channel Vulnerabilities Introduced by RowHammer Defenses
  di: Bostancı, F. Nisa, et al.
  Pubblicazione: (2025)
• BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron
  di: Miah, Abdullah Arafat, et al.
  Pubblicazione: (2026)