Haoran Gao

collaborators

Showing cs.CRShow all

3 papers · 1 filter

cs.CR2026

BadDLM: Backdooring Diffusion Language Models with Diverse Targets

Shengfang Zhai, Xiaoyang Ji, Yuling Shi +6

Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional co…

cs.CR2025

Resource Consumption Red-Teaming for Large Vision-Language Models

Haoran Gao, Yuanhe Zhang, Zhenhong Zhou +7

Resource Consumption Attacks (RCAs) have emerged as a significant threat to the deployment of Large Language Models (LLMs). With the integration of vision modalities, additional at…

cs.CR2025

$P D^{3} F$ : A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models

Yuanhe Zhang, Xinyue Wang, Haoran Gao +4

Large Language Models (LLMs), due to substantial computational requirements, are vulnerable to resource consumption attacks, which can severely degrade server performance or even c…

BadDLM: Backdooring Diffusion Language Models with Diverse Targets

Resource Consumption Red-Teaming for Large Vision-Language Models

PD3F: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models

$P D^{3} F$ : A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models