Xingjun Ma

SIDE: Surrogate Conditional Data Extraction from Diffusion Models AAAI 2026 Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with Constraints ACL 2026 Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models AAAI 2026 IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves ICCV 2025 X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP ICML 2025 Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models CVPR 2025 TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models CVPR 2025 Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks CVPR 2025 BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks ICLR 2025 Detecting Backdoor Samples in Contrastive Language Image Pretraining ICLR 2025 Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models EMNLP 2025 StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025 Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation ICCV 2025 AIM: Additional Image Guided Generation of Transferable Adversarial Attacks AAAI 2025 HoneypotNet: Backdoor Attacks Against Model Extraction AAAI 2025 CALM: Curiosity-Driven Auditing for Large Language Models AAAI 2025 Fake Alignment: Are LLMs Really Aligned Well? NAACL 2024 Constrained Intrinsic Motivation for Reinforcement Learning IJCAI 2024 UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation NIPS 2024 Adversarial Prompt Tuning for Vision-Language Models ECCV 2024 LDReg: Local Dimensionality Regularized Self-Supervised Learning ICLR 2024 Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples CVPR 2023 Distilling Cognitive Backdoor Patterns within an Image ICLR 2023 Reconstructive Neuron Pruning for Backdoor Defense ICML 2023 Transferable Unlearnable Examples ICLR 2023 Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022 CalFAT: Calibrated Federated Adversarial Training with Label Skewness NIPS 2022 Few-Shot Backdoor Attacks on Visual Object Tracking ICLR 2022 Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks ICLR 2021 Noise Doesn't Lie: Towards Universal Detection of Deep Inpainting IJCAI 2021 Unlearnable Examples: Making Personal Data Unexploitable ICLR 2021 Improving Adversarial Robustness via Channel-wise Activation Suppressing ICLR 2021 Anti-Backdoor Learning: Training Clean Models on Poisoned Data NIPS 2021 Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning NIPS 2021 Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better ICCV 2021 $\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression NIPS 2021 Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks NIPS 2021 Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets ICLR 2020 Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks ECCV 2020 Normalized Loss Functions for Deep Learning with Noisy Labels ICML 2020 Short-Term and Long-Term Context Aggregation Network for Video Inpainting ECCV 2020 Clean-Label Backdoor Attacks on Video Recognition Models CVPR 2020 Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles CVPR 2020 Improving Adversarial Robustness Requires Revisiting Misclassified Examples ICLR 2020 Generative Image Inpainting with Submanifold Alignment IJCAI 2019 On the Convergence and Robustness of Adversarial Training ICML 2019 Symmetric Cross Entropy for Robust Learning With Noisy Labels ICCV 2019 Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality ICLR 2018 Dimensionality-Driven Learning with Noisy Labels ICML 2018 Iterative Learning With Open-Set Noisy Labels CVPR 2018 Adversarial Generation of Real-time Feedback with Neural Networks for Simulation-based Training IJCAI 2017