Publications

"Reconstructing Template-Memorized Images from Natural Prompts." International Conference on Machine Learning (ICML). 2026.

arXiv

"Universal Jailbreak Suffixes Are Strong Attention Hijackers." Transactions of the Association for Computational Linguistics (TACL). 2026.

arXiv Code

"Safeguarding Language Models via Self-Destruct Trapdoor." Conference of the European Chapter of the Association for Computational Linguistics (EACL). 2026.

PDF Code

"Accessorize in the Dark: A Security Analysis of Near-Infrared Face Recognition." European Symposium on Research in Computer Security (ESORICS). 2023.

PDF Code

"Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters." Workshop on Challenges in Deploying and monitoring Machine Learning Systems (DMML@NeurIPS). 2022.

PDF

"Scalable Verification of GNN-based Job Schedulers." International Conference on Object-Oriented Programming, Systems, Languages & Applications (OOPSLA). 2022.

PDF arXiv Code

"On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples." The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security (CVPRW). 2018.

PDF arXiv

"Self-Confidence Trumps Knowledge: A Cross-Cultural Study of Security Behavior." ACM Conference on Human Factors in Computing Systems (CHI). 2017. Equal contribution by the first two authors.

PDF Aux