"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks
Paper • 2204.04636 • Published • 1
Edoardo Mosca
EdoardoMosca
AI & ML interests
Large Language Models, Efficient Fine-Tuning, Post-Hoc Explainability
Recent Activity
liked a Space 11 days ago
HuggingFaceFW/finephrase liked a Space 17 days ago
OpenEvals/evaluation-guidebook liked a model 28 days ago
LiquidAI/LFM2-24B-A2BOrganizations
authored a
paper over 2 years ago