ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Xiaojun Jia

Xiaojun Jia

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 1:13 AM AMS

14

papers

529

total citations

papers (14)

LAS-AT: Adversarial Training With Learnable Attack Strategy

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models

A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection

Prior-Guided Adversarial Initialization for Fast Adversarial Training

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

Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal

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

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

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