6 papers
The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
Mingrui Liu, Sixiao Zhang, Cheng Long +1
As Large Language Models (LLMs) become integral to computing infrastructure, safety alignment serves as the primary security control preventing the generation of harmful payloads.…
MPRU: Modular Projection-Redistribution Unlearning as Output Filter for Classification Pipelines
Minyi Peng, Darian Gunamardi, Ivan Tjuawinata +1
As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. Howeve…
A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
Jiale Guo, Suizhi Huang, Mei Li +8
The integration of Large Language Models (LLMs) into software engineering has driven a transition from traditional rule-based systems to autonomous agentic systems capable of solvi…
Time Series Analysis in Frequency Domain: A Survey of Open Challenges, Opportunities and Benchmarks
Qianru Zhang, Yuting Sun, Honggang Wen +6
Frequency-domain analysis has emerged as a powerful paradigm for time series analysis, offering unique advantages over traditional time-domain approaches while introducing new theo…
Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems
Chin Yuen Kwok, Jia Qi Yip, Zhen Qiu +2
Audio deepfake detection (ADD) models are commonly evaluated using datasets that combine multiple synthesizers, with performance reported as a single Equal Error Rate (EER). Howeve…
Edge-Assisted Collaborative Fine-Tuning for Multi-User Personalized Artificial Intelligence Generated Content (AIGC)
Nan Li, Wanting Yang, Marie Siew +4
Diffusion models (DMs) have emerged as powerful tools for high-quality content generation, yet their intensive computational requirements for inference pose challenges for resource…