Xiaojun Jia

10

Papers

160

Total Citations

Papers (10)

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

Perception-Guided Jailbreak Against Text-to-Image Models

Does Few-Shot Learning Suffer from Backdoor Attacks?

Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

NeurIPS 2025arXiv

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation

AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts

Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds