Benjamin I. P. Rubinstein

~Benjamin_I._P._Rubinstein1

9

论文总数

4.5

年均投稿

5.8

平均评分

接收情况5/9

会议分布

ICLR

5

NeurIPS

3

ICML

1

发表论文 (9 篇)

20256 篇

Adaptive Data Analysis for Growing Data

NeurIPS 2025Poster

DDAD: A Two-Pronged Adversarial Defense Based on Distributional Discrepancy

ICLR 2025Rejected

One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy

ICML 2025Poster

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness

NeurIPS 2025Poster

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning

ICLR 2025Poster

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

ICLR 2025withdrawn

20243 篇

Getting a-Round Guarantees: Floating-Point Attacks on Certified Robustness

ICLR 2024withdrawn

Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models

NeurIPS 2024Poster

The Certification Paradox: Certifications Admit Better Evasion Attacks

ICLR 2024Rejected

合作者 (19)

Olga Ohrimenko3 篇

Andrew Craig Cullen2 篇

Paul Montague2 篇

Sarah Monazam Erfani2 篇

Shijie Liu2 篇

Neil G Marchant2 篇

Jiacheng Zhang2 篇