activity
20242026
collaborators

5 papers

cs.CR2026

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment

Yuxi Li, Yi Liu, Yuekang Li +4

Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Current safety alignment techniques, how…

cs.CR2025

Efficient Detection of Toxic Prompts in Large Language Models

Yi Liu, Junzhe Yu, Huijia Sun +4

Large language models (LLMs) like ChatGPT and Gemini have significantly advanced natural language processing, enabling various applications such as chatbots and automated content g…

cs.CR2025

Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Models

Junzhe Yu, Yi Liu, Huijia Sun +2

Large Language Models (LLMs) have significantly advanced text understanding and generation, becoming integral to applications across education, software development, healthcare, en…

cs.CR2024

MiniScope: Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis

Shenao Wang, Yuekang Li, Kailong Wang +4

The advent of MiniApps, operating within larger SuperApps, has revolutionized user experiences by offering a wide range of services without the need for individual app downloads. H…

cs.CR2024

Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment

Jie Li, Yi Liu, Chongyang Liu +4

Large Language Models (LLMs) like OpenAI's GPT series, Anthropic's Claude, and Meta's LLaMa have shown remarkable capabilities in text generation. However, their susceptibility to…