"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 model 2 days ago
LiquidAI/LFM2.5-350M liked a Space 20 days ago
HuggingFaceFW/finephrase liked a Space 26 days ago
OpenEvals/evaluation-guidebookOrganizations
authored a
paper almost 3 years ago