|
Workshop
|
|
Does Refusal Training in LLMs Generalize to the Past Tense?
Maksym Andriushchenko · Nicolas Flammarion
|
|
|
Workshop
|
|
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
Stanislav Fort · Balaji Lakshminarayanan
|
|
|
Poster
|
Wed 16:30
|
Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
David Woodruff · Samson Zhou
|
|
|
Poster
|
Wed 16:30
|
The Price of Implicit Bias in Adversarially Robust Generalization
Nikolaos Tsilivis · Natalie Frank · Nati Srebro · Julia Kempe
|
|
|
Poster
|
Thu 11:00
|
TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
Zhen Chen · Yi Zhang · Fu Wang · Xingyu Zhao · Xiaowei Huang · Wenjie Ruan
|
|
|
Poster
|
Fri 16:30
|
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
Kaibo Zhang · Yunjuan Wang · Raman Arora
|
|
|
Poster
|
Thu 11:00
|
RAMP: Boosting Adversarial Robustness Against Multiple lp Perturbations for Universal Robustness
Enyi Jiang · Gagandeep Singh
|
|
|
Poster
|
Thu 16:30
|
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
Thibault Simonetto · Salah GHAMIZI · Maxime Cordy
|
|
|
Poster
|
Thu 11:00
|
Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
Fatemeh Nourilenjan Nokabadi · Christian Gagné · Jean-Francois Lalonde
|
|
|
Poster
|
Fri 11:00
|
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
Shuyao Li · Sushrut Karmalkar · Ilias Diakonikolas · Jelena Diakonikolas
|
|
|
Workshop
|
|
Between the Bars: Gradient-based Jailbreaks are Bugs that induce Features
Kaivalya Hariharan · Uzay Girit
|
|
|
Poster
|
Wed 16:30
|
Robust Neural Contextual Bandit against Adversarial Corruptions
Yunzhe Qi · Yikun Ban · Arindam Banerjee · Jingrui He
|
|
