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.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
European Association for Computational Linguistics (EACL)
Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language Models
IEEE Transactions on Dependable and Secure Computing Backdoor Complications: A Comprehensive Analysis and Mitigation of the Unforeseen Consequences of Backdoor Attacks
National Conference of the American Association for Artificial Intelligence (AAAI)
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
Conference on Neural Information Processing Systems (NeurIPS)
Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
Conference on Neural Information Processing Systems (NeurIPS)
Finding and Reactivating Post-Trained LLMs’ Hidden Safety Mechanisms
Conference on Empirical Methods in Natural Language Processing (EMNLP)
Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification
IEEE International Conference on Computer Vision (ICCV)
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
ACM Conference on Computer and Communications Security (CCS)
UnsafeBench: Benchmarking Image Safety Classifiers onReal-World and AI-Generated Images
IEEE Transactions on Dependable and Secure Computing Revealing the Risk of Hyper-parameter Leakage in Deep Reinforcement Learning Models