Qibing Ren
6 papers · 2022–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
🔥
Unstoppable · Bronze
Venues
Top co-authors
Research topics
Keywords
adversarial attack
(4)
large language model
(2)
safety alignment
(2)
code completion
(1)
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)
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
Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond
CVPR 2022
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain
NeurIPS 2022