Faculty
2022: Busy Beaver Award für "Privacy of Machine Learning"
2019: Best paper award at NDSS
Dr. Yang Zhang ist Faculty am CISPA. Seine Forschung konzentriert sich auf Trustworthy Machine Learning (Privacy, Safety und Security). Außerdem arbeitet er an der Messung und dem Verständnis von Fehlinformationen und unsicheren Inhalten wie hasserfüllten Memes im Internet. Im Laufe der Jahre hat er zahlreiche Paper auf Spitzenkonferenzen in Informatik, einschließlich CCS, NDSS, Oakland und USENIX Security veröffentlicht. Seine Arbeit hat 2019 den NDSS Distinguished Paper Award und 2022 den CCS Best Paper Award Runner-up erhalten.
Foundations and Trends® in Privacy and Security Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
ACM Conference on Computer and Communications Security (CCS)
MGTBench: Benchmarking Machine-Generated Text Detection
ACM Conference on Computer and Communications Security (CCS)
BadMerging: Backdoor Attacks Against Model Merging
ACM Conference on Computer and Communications Security (CCS)
LAMPS '24: ACM CCS Workshop on Large AI Systems and Models with Privacy and Safety Analysis
Conference on Empirical Methods in Natural Language Processing (EMNLP)
The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective
Conference on Empirical Methods in Natural Language Processing (EMNLP)
ModScan: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities
European Conference on Artificial Intelligence (ECAI)
Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
ACM Conference on Computer and Communications Security (CCS)
Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution
ACM Conference on Computer and Communications Security (CCS)
ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models
ACM Conference on Computer and Communications Security (CCS)
Membership Inference Attacks Against In-Context Learning