◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

yunrui yu

Trustworthy AI

4 papers hereh-index 485 citations9 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author4

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG4
affiliations
  • Trustworthy AI
ORCID 0009-0003-2224-2414

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.LG2026

Dummy-Aware Weighted Attack (DAWA): Breaking the Safe Sink in Dummy Class Defenses

Yunrui Yu, Xuxiang Feng, Pengda Qin +5

Adversarial robustness evaluation faces a critical challenge as new defense paradigms emerge that can exploit limitations in existing assessment methods. This paper reveals that Du…

cs.LG2026

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness

Yunrui Yu, Hang Su, Jun Zhu

This work investigates the critical role of activation function curvature -- quantified by the maximum second derivative max∣I¨ƒ′′∣ -- in adversarial robustness. Using the Recurs…

cs.LG2025

RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function

Yunrui Yu, Kafeng Wang, Hang Su +1

Despite their widespread success, deep neural networks remain critically vulnerable to adversarial attacks, posing significant risks in safety-sensitive applications. This paper in…

cs.LG2025

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss

Yunrui Yu, Hang Su, Cheng-zhong Xu +2

Gradient-based adversarial attacks using the Cross-Entropy (CE) loss often suffer from overestimation due to relative errors in gradient computation induced by floating-point arith…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.