Shiqing Ma

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models ACL 2026 From Chaos to Clarity: A Knowledge Graph-Driven Audit Dataset Generation Framework for LLM Unlearning AAAI 2026 PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and VLM-Guided Optimization CVPR 2026 An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025 Data-centric NLP Backdoor Defense from the Lens of Memorization NAACL 2025 Invisible Backdoor Attack against Self-supervised Learning CVPR 2025 MLLM-as-a-Judge for Image Safety without Human Labeling CVPR 2025 STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning ICLR 2025 The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation ACL 2025 Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone CVPR 2025 Token-Budget-Aware LLM Reasoning ACL 2025 DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models ICLR 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 How to Trace Latent Generative Model Generated Images without Artificial Watermark? ICML 2024 LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024 Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation CVPR 2024 UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening ECCV 2024 Detecting Backdoors in Pre-Trained Encoders CVPR 2023 Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration NeurIPS 2023 FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning ICLR 2023 NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models ACL 2023 UNICORN: A Unified Backdoor Trigger Inversion Framework ICLR 2023 Where Did I Come From? Origin Attribution of AI-Generated Images NeurIPS 2023 Better Trigger Inversion Optimization in Backdoor Scanning CVPR 2022 BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning CVPR 2022 Complex Backdoor Detection by Symmetric Feature Differencing CVPR 2022 Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense ICML 2022 Rethinking the Reverse-engineering of Trojan Triggers NeurIPS 2022 Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NeurIPS 2022 Backdoor Scanning for Deep Neural Networks through K-Arm Optimization ICML 2021 Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification AAAI 2021 Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples NeurIPS 2018