6 papers
Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
Yuhan Zhi, Longtian Wang, Xiaofei Xie +3
Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attri…
TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
Longtian Wang, Xiaofei Xie, Tianlin Li +2
Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW…
Benchmarking and Revisiting Code Generation Assessment: A Mutation-Based Approach
Longtian Wang, Tianlin Li, Xiaofei Xie +3
Code Large Language Models (CLLMs) have exhibited outstanding performance in program synthesis, attracting the focus of the research community. The evaluation of CLLM's program syn…
Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
Chenhao Lin, Chenyang Zhao, Shiwei Wang +3
Backdoor attacks typically place a specific trigger on certain training data, such that the model makes prediction errors on inputs with that trigger during inference. Despite the…
Exposing Product Bias in LLM Investment Recommendation
Yuhan Zhi, Xiaoyu Zhang, Longtian Wang +4
Large language models (LLMs), as a new generation of recommendation engines, possess powerful summarization and data analysis capabilities, surpassing traditional recommendation sy…
StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation
Xiaoming Liu, Chen Liu, Zhaohan Zhang +4
Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this appr…