Xiaojun Jia

34 papers · 2019–2026 · 10 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (8) 🏃 Academic Marathon (6) 🌍 Conference Polyglot (10) 🗺️ Taxonomy Completionist (41)

🗺️ Taxonomy Completionist (41) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🔬 Deep Specialist (15) 🤝 Dynamic Duo (12) 🧬 Topic Evolution 🏆 Keyword Champion (3) ⚡ Prolific Year (15) 💎 Century Club (28) 🔥 Unstoppable (5) 🗃️ Keyword Collector (123) 📈 Trend Setter ❓ The Questioner

Conferences

AAAI (9) ECCV (4) ICCV (4) ACL (3) CVPR (3) EMNLP (3) ICLR (3) ICML (2) NAACL (2) INTERSPEECH (1)

Top co-authors

Xiaochun Cao (13) Siyuan Liang (6) Yang Liu (6) Yihao Huang (5) Jindong Gu (5) Simeng Qin (5) Ranjie Duan (5) Xinwei Liu (4) Ke Ma (3) Qing Guo (3)

Research topics

Privacy (2)

Keywords

adversarial attack (9) jailbreak attack (5) adversarial perturbation (4) multimodal large language model (3) security vulnerability (3) adversarial prompt (3) adversarial example (3) adversarial learning (3) multimodal learning (3) toxicity maximization (2) autonomous driving (2) 3d point cloud (2) large language model (2) large vision language model (2) text-to-image model (2) black-box attack (2) adversarial training (2) backdoor attack (2) vision language model (2) imperceptible perturbation (2)

Papers

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations AAAI 2026 AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin AAAI 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 The Emotional Baby Is Truly Deadly: Does Your Multimodal Large Reasoning Model Have Emotional Flattery Towards Humans? AAAI 2026 GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models ACL 2026 AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts ICCV 2025 Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025 Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization ACL 2025 Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings ACL 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization EMNLP 2025 LLM Jailbreak Detection for (Almost) Free! EMNLP 2025 One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems EMNLP 2025 Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning ICCV 2025 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation ICCV 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 DAMA: Data- and Model-aware Alignment of Multi-modal LLMs ICML 2025 Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs ICML 2025 TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025 Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory ECCV 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 Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024 Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats ICLR 2023 Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training INTERSPEECH 2023 Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization AAAI 2023 Prior-Guided Adversarial Initialization for Fast Adversarial Training ECCV 2022 Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal ECCV 2022 Defending against Model Stealing via Verifying Embedded External Features AAAI 2022 A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection ECCV 2022 LAS-AT: Adversarial Training With Learnable Attack Strategy CVPR 2022 ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples CVPR 2019