ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Xiaogeng Liu

Xiaogeng Liu

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 14, 2026, 11:22 PM AMS

7

papers

1,046

total citations

papers (7)

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents

NEURIPS 2025arXiv

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines