Skip to content
conftrace_

Zhan Qin

13 papers · 2021–2026 · 8 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 ↓
+4 more ↓ πŸ—ΊοΈ Taxonomy Completionist (17) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🧬 Topic Evolution
πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (53) πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze

Venues

ICLR (3) AAAI (2) ACL (2) ICCV (2) CVPR (1) EMNLP (1) ICML (1) NeurIPS (1)

Top co-authors

Kui Ren (8) Wenjie Wang (3) Shuo Shao (3) Yiming Li (3) Jian Lou (3) Sibei Yang (2) Kunzhe Huang (2) Minlie Huang (1) Lan Tao (1) Zijian Zhang (1)

Research topics

Machine Learning (9) Artificial Intelligence (8) Core AI (7) Application Areas (6) Optimization & Theory (4) Learning Types (2) Computer Vision (1) Deep Learning (1) Interdisciplinary (1) Generation (1) Learning Paradigms (1) Social (1) Techniques (1)

Keywords

jailbreak attack (3) attack success rate (2) large language model (2) backdoor attack (2) machine unlearning (2) backdoor defense (2) adversarial attack (2) text-to-image generation (1) adversarial training (1) adversarial robustness (1) ai safety (1) safety alignment (1) mutual information (1) feature space (1) minimax optimization (1) model editing (1) self-supervised learning (1) hessian approximation (1) data privacy (1) information entropy (1)

Papers

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization AAAI 2026 JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization CVPR 2026 MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies AAAI 2026 DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing ACL 2025 Don’t 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 NeurIPS 2023 MUter: Machine Unlearning on Adversarially Trained Models ICCV 2023 Backdoor Defense via Decoupling the Training Process ICLR 2022 Feature Importance-Aware Transferable Adversarial Attacks ICCV 2021 From Local to Global Norm Emergence: Dissolving Self-reinforcing Substructures with Incremental Social Instruments ICML 2021