Zhan Qin
12 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10) π§ Keyword Pioneer
π
Academic Marathon
(5)
π
Grand Slam
π₯
Unstoppable
(5)
π
Century Club
(10)
Conferences
ICLR (3)
AAAI (2)
ACL (2)
ICCV (2)
EMNLP (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
attack success rate
(2)
machine unlearning
(2)
large language model
(2)
jailbreak attack
(2)
minimax optimization
(1)
ai safety
(1)
safety alignment
(1)
mutual information
(1)
markov chain
(1)
semantic space
(1)
information entropy
(1)
hessian approximation
(1)
data privacy
(1)
adversarial attack
(1)
black-box attack
(1)
generalization bound
(1)
text embedding
(1)
parameter update
(1)
privacy protection
(1)
transferable adversarial example
(1)
Papers
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
AAAI 2026
Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
AAAI 2026
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
ACL 2025
Donβt Say No: Jailbreaking LLM by Suppressing Refusal
ACL 2025
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
ICLR 2025
Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models
EMNLP 2024
Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
ICLR 2024
Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
NIPS 2023
MUter: Machine Unlearning on Adversarially Trained Models
ICCV 2023
Backdoor Defense via Decoupling the Training Process
ICLR 2022
From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments
ICML 2021
Feature Importance-Aware Transferable Adversarial Attacks
ICCV 2021