Qibing Ren
6 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π§
Keyword Pioneer
π
Conference Polyglot
(4)
π
Cross-Pollinator
(12)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(12)
Conferences
ACL (3)
CVPR (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
adversarial attack
(3)
large language model
(2)
safety alignment
(2)
data augmentation
(1)
adversarial training
(1)
model alignment
(1)
distribution shift
(1)
convolutional neural network
(1)
low-rank adaptation
(1)
frequency domain
(1)
red teaming
(1)
shapley value
(1)
keypoint detection
(1)
llm safety
(1)
attack success rate
(1)
safety training
(1)
safety vulnerability
(1)
ethical reasoning
(1)
defense strategy
(1)
adversarial robustness
(1)
Papers
Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs
ACL 2026
LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
ACL 2025
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
ACL 2024
ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
ICLR 2023
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain
NIPS 2022
Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond
CVPR 2022