9 papers
Automated Detection of Abnormalities in Zebrafish Development
Sarath Sivaprasad, Hui-Po Wang, Anna-Lisa Jäckel +4
Zebrafish embryos are a valuable model for drug discovery due to their optical transparency and genetic similarity to humans. However, current evaluations rely on manual inspection…
ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks
Zhixiong Zhuang, Maria-Irina Nicolae, Hui-Po Wang +1
The integration of large language models (LLMs) into a wide range of applications has highlighted the critical role of well-crafted system prompts, which require extensive testing…
Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
Sai Suresh Macharla Vasu, Ivaxi Sheth, Hui-Po Wang +2
The adoption of large language models (LLMs) is transforming the peer review process, from assisting reviewers in writing detailed evaluations to generating entire reviews automati…
Stealix: Model Stealing via Prompt Evolution
Zhixiong Zhuang, Hui-Po Wang, Maria-Irina Nicolae +1
Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing int…
DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators
Tejumade Afonja, Hui-Po Wang, Raouf Kerkouche +1
Generating tabular data under differential privacy (DP) protection ensures theoretical privacy guarantees but poses challenges for training machine learning models, primarily due t…
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Hui-Po Wang, Mario Fritz
Despite the widespread use of statistical prior models in various fields, such models for neural network gradients have long been overlooked. The inherent challenge stems from thei…