Toggle Poster Visibility
In-Person Oral presentation / top 25% paper
Mon May 01 01:00 AM -- 01:10 AM (PDT) @ AD11 None
Quantifying Memorization Across Neural Language Models
In-Person Oral presentation / top 25% paper
Mon May 01 01:10 AM -- 01:20 AM (PDT) @ AD11 None
Human-Guided Fair Classification for Natural Language Processing
In-Person Oral presentation / top 25% paper
Mon May 01 01:20 AM -- 01:30 AM (PDT) @ AD11 None
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
In-Person Oral presentation / top 5% paper
Mon May 01 01:30 AM -- 01:40 AM (PDT) @ AD11 None
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
In-Person Oral presentation / top 25% paper
Mon May 01 01:40 AM -- 01:50 AM (PDT) @ AD11 None
UNICORN: A Unified Backdoor Trigger Inversion Framework
In-Person Oral presentation / top 25% paper
Mon May 01 01:50 AM -- 02:00 AM (PDT) @ AD11 None
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
In-Person Oral presentation / top 25% paper
Mon May 01 02:00 AM -- 02:10 AM (PDT) @ AD11 None
Learning to Estimate Shapley Values with Vision Transformers
In-Person Oral presentation / top 25% paper
Mon May 01 02:10 AM -- 02:20 AM (PDT) @ AD11 None
Provable Defense Against Geometric Transformations