5 papers
Confidence-Adaptive SwiGLU for Mixture-of-Experts
Shaohua Li, Xiuchao Sui, Xiaobing Sun +4
SwiGLU has become a standard gated activation in modern Transformer MLPs, yet its gate sharpness -- the smoothness and selectivity of the gating function -- is typically fixed thro…
Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
Yingzhi Xia, Setthakorn Tanomkiattikun, Liangli Zhen +1
Diffusion models (DMs) have recently shown remarkable performance on inverse problems (IPs). Optimization-based methods can fast solve IPs using DMs as powerful regularizers, but t…
Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models
Xiaobing Sun, Perry Lam, Shaohua Li +4
Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obf…
Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
Lei Jiang, Zixun Zhang, Zizhou Wang +4
Large Vision-Language Models (LVLMs) demonstrate exceptional performance across multimodal tasks, yet remain vulnerable to jailbreak attacks that bypass built-in safety mechanisms…
Global Challenge for Safe and Secure LLMs Track 1
Xiaojun Jia, Yihao Huang, Yang Liu +27
This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme…