Xiaojun Jia

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin AAAI 2026 GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models ACL 2026 GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations AAAI 2026 Hidden Dangers of Compositional Generation: Diagnosing Semantic Safety Failures in Text-to-Image Models CVPR 2026 MPAS: Breaking Sequential Constraints of Multi-Agent Communication Topologies via Individual-Epistemic Message Propagation AAAI 2026 PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems AAAI 2026 Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack CVPR 2026 The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans? AAAI 2026 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation ICCV 2025 Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning ICCV 2025 AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts ICCV 2025 Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs ICML 2025 Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings ACL 2025 DAMA: Data- and Model-aware Alignment of Multi-modal LLMs ICML 2025 Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization ACL 2025 Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models ICCV 2025 Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025 LLM Jailbreak Detection for (Almost) Free! EMNLP 2025 One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems EMNLP 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization EMNLP 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025 Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025 TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025 Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory ECCV 2024 Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024 Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds CVPR 2024 Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection ICLR 2024 Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization AAAI 2023 Inequality phenomenon in l_∞-adversarial training, and its unrealized threats ICLR 2023 Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training Interspeech 2023 A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection ECCV 2022 Defending against Model Stealing via Verifying Embedded External Features AAAI 2022 LAS-AT: Adversarial Training With Learnable Attack Strategy CVPR 2022 Prior-Guided Adversarial Initialization for Fast Adversarial Training ECCV 2022 Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal ECCV 2022 ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples CVPR 2019