8 papers
When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning
Yuanhe Zhang, Ziwei Wang, Jie Ren +6
Large reasoning models (LRMs) improve performance on complex tasks through extended reasoning, yet the same process can degenerate into redundant verification and persistent genera…
Uncovering Uncontrolled Repetition through Residual Stream Dynamics
Yuanhe Zhang, Xinyao Zhou, Haoran Gao +5
Uncontrolled repetition can prolong autoregressive generation in large language models (LLMs) and enable resource consumption attacks. Prior analyses of repetitive generation have…
From Inaudible Inputs to Model Failures: Low-Frequency Safety Risks in LALMs
Yuanhe Zhang, Weiliu Wang, Jie Ren +7
Large audio-language models (LALMs) have demonstrated strong capabilities in understanding diverse audio inputs. This diversity includes low-frequency signals that are inaudible to…
Structure-Guided Visual Perturbation Neutralization for LVLMs
Yuanhe Zhang, Xueting Wang, YanBin Ren +6
Image inputs enable Large Vision Language Models (LVLMs) to perceive fine-grained visual information, but also introduce a pixel-level attack surface through which adversarial pert…
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…
From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
Xinyue Wang, Yuanhe Zhang, Zhengshuo Gong +6
The enhanced capabilities of LLM-based agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM alignment, agents…
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…
: 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…