ADMIn: Attacks on Dataset, Model and Input. A Threat Model for AI Based Software

Documenti analoghi

• A Relevance Model for Threat-Centric Ranking of Cybersecurity Vulnerabilities
  di: McCoy, Corren, et al.
  Pubblicazione: (2024)
• Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack
  di: Chen, Guanzhong, et al.
  Pubblicazione: (2024)
• Predicting known Vulnerabilities from Attack News: A Transformer-Based Approach
  di: Othman, Refat, et al.
  Pubblicazione: (2026)
• Active Authentication via Korean Keystrokes Under Varying LLM Assistance and Cognitive Contexts
  di: Roh, Dong Hyun, et al.
  Pubblicazione: (2025)
• I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference
  di: Gao, Zibo, et al.
  Pubblicazione: (2025)