Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications

Documenti analoghi

• Uncovering Hidden Systematics in Neural Network Models for High Energy Physics
  di: Flek, Lucie, et al.
  Pubblicazione: (2026)
• Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations
  di: Saala, Timo, et al.
  Pubblicazione: (2025)
• MiniFool -- Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks
  di: Flek, Lucie, et al.
  Pubblicazione: (2025)
• Introduction to the Usage of Open Data from the Large Hadron Collider for Computer Scientists in the Context of Machine Learning
  di: Saala, Timo, et al.
  Pubblicazione: (2025)
• Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction
  di: Rawat, Shivam, et al.
  Pubblicazione: (2025)