52 citations · 60 across the 15 of their papers we have counts for
10 papers · 1 filter
FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
Jiaming Zhang, Zherui Li, Siqi Guo +3
As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves as both a perceptual input and…
Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain
Daizong Liu, Junhao Dong, Zhiyuan Ma +6
Multimodal large language models (MLLMs) have extended the capability of large language models (LLMs) to process more contextual multimodal information, showing remarkable progress…
EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams
Zixuan Chen, Jiakai Zhang, Junhao Dong +4
Event cameras, with high temporal resolution, high dynamic range, and asynchronous sensing characteristics, have shown great potential for dense 3D reconstruction. Traditional reco…
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Jiaming Zhang, Boyang Chen, Zherui Li +14
Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technica…
Unifying Adversarially Robust Model Experts in Vision-Language Models
Nguyen Duc Thai, Junhao Dong, Sua Qi Rong +2
Vision-language models (VLMs), such as CLIP, are vulnerable to adversarial attacks, posing a serious problem for real-life applications and deployment. Adversarial fine-tuning emer…
Adaptive Probe-based Steering for Robust LLM Jailbreaking
Junxi Chen, Junhao Dong, Xiaohua Xie
Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased co…
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
Shen Lin, Junhao Dong, Rongjie Chen +3
Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-s…
EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation
Liang Lin, Chunxi Luo, Kaiwen Luo +12
Large Audio Language Models (LALMs) remain vulnerable to acoustic noise, which can obscure task-relevant evidence and produce unreliable responses. We propose EchoDistill, a noisy-…
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
Kaiwen Luo, Zhenhong Zhou, Leyan Wang +32
Advances in Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs). Among these, Large Audio Language Models (LALMs) are essential for realizi…
Hierarchically Robust Zero-shot Vision-language Models
Junhao Dong, Yifei Zhang, Hao Zhu +2
Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approach…