activity
20242026
most citedMetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

1 citations · 1 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CR20261 cited

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

Wentian Zhu, Zhen Xiang, Wei Niu +1

Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Langu…

cs.CL2026

Green Shielding: A User-Centric Approach Towards Trustworthy AI

Aaron J. Li, Nicolas Sanchez, Hao Huang +8

Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well…

cs.LG2026

SoSBench: Benchmarking Safety Alignment on Six Scientific Domains

Fengqing Jiang, Fengbo Ma, Zhangchen Xu +8

Large language models (LLMs) exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particul…

cs.LG2026

Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment

Qitao Tan, Xiaoying Song, Ningxi Cheng +6

Public large language models (LLMs) are typically safety-aligned during pretraining, yet task-specific fine-tuning required for deployment often erodes this alignment and introduce…

cs.LG2025

GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Zhen Xiang, Linzhi Zheng, Yanjie Li +9

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail ag…

cs.CL2025

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Chejian Xu, Jiawei Zhang, Zhaorun Chen +22

Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have re…