AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines

Documenti analoghi

• Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems
  di: Rathnasuriya, Ravishka, et al.
  Pubblicazione: (2025)
• Efficiency Robustness of Dynamic Deep Learning Systems
  di: Rathnasuriya, Ravishka, et al.
  Pubblicazione: (2025)
• Impact Analysis of Inference Time Attack of Perception Sensors on Autonomous Vehicles
  di: Chen, Hanlin, et al.
  Pubblicazione: (2025)
• AdaDoS: Adaptive DoS Attack via Deep Adversarial Reinforcement Learning in SDN
  di: Shao, Wei, et al.
  Pubblicazione: (2025)
• Energy-Latency Attacks: A New Adversarial Threat to Deep Learning
  di: Meftah, Hanene F. Z. Brachemi, et al.
  Pubblicazione: (2025)