| FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks T Lorenz, M Kwiatkowska, M Fritz arXiv preprint arXiv:2406.11522, 2024 | | 2024 |
| Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition E Debenedetti, J Rando, D Paleka, SF Florin, D Albastroiu, N Cohen, ... arXiv preprint arXiv:2406.07954, 2024 | | 2024 |
| MultiMax: Sparse and Multi-Modal Attention Learning Y Zhou, M Fritz, M Keuper arXiv preprint arXiv:2406.01189, 2024 | | 2024 |
| Are you still on track!? Catching LLM Task Drift with Activations S Abdelnabi, A Fay, G Cherubin, A Salem, M Fritz, A Paverd arXiv preprint arXiv:2406.00799, 2024 | 1 | 2024 |
| Stealthy Imitation: Reward-guided Environment-free Policy Stealing Z Zhuang, MI Nicolae, M Fritz arXiv preprint arXiv:2405.07004, 2024 | | 2024 |
| CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models H Hajipour, K Hassler, T Holz, L Schönherr, M Fritz 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 684-709, 2024 | 21* | 2024 |
| PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics D Zhu, D Chen, Q Li, Z Chen, L Ma, J Grossklags, M Fritz arXiv preprint arXiv:2404.04722, 2024 | 1 | 2024 |
| Can LLMs Separate Instructions From Data? And What Do We Even Mean By That? E Zverev, S Abdelnabi, M Fritz, CH Lampert arXiv preprint arXiv:2403.06833, 2024 | 5 | 2024 |
| LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History A Gupta, I Sheth, V Raina, M Gales, M Fritz arXiv preprint arXiv:2402.18216, 2024 | | 2024 |
| Exploring Value Biases: How LLMs Deviate Towards the Ideal S Sivaprasad, P Kaushik, S Abdelnabi, M Fritz arXiv preprint arXiv:2402.11005, 2024 | | 2024 |
| Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing A Anani, T Lorenz, B Schiele, M Fritz arXiv preprint arXiv:2402.08400, 2024 | | 2024 |
| Towards biologically plausible and private gene expression data generation D Chen, M Oestreich, T Afonja, R Kerkouche, M Becker, M Fritz arXiv preprint arXiv:2402.04912, 2024 | 1 | 2024 |
| B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers M Böhle, N Singh, M Fritz, B Schiele IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024 | 6 | 2024 |
| On Adversarial Training without Perturbing all Examples M Losch, M Omran, D Stutz, M Fritz, B Schiele CISPA, 2024 | | 2024 |
| Privacy-aware document visual question answering R Tito, K Nguyen, M Tobaben, R Kerkouche, MA Souibgui, K Jung, ... arXiv preprint arXiv:2312.10108, 2023 | 4 | 2023 |
| 7th ACM Computer Science in Cars Symposium December 5, 2023 Darmstadt University of Applied Sciences, Germany SN Spencer, B Brücher, C Krauß, M Fritz, HJ Hof, O Wasenmüller | | 2023 |
| From Attachments to SEO: Click Here to Learn More about Clickbait PDFs! G Stivala, S Abdelnabi, A Mengascini, M Graziano, M Fritz, G Pellegrino Proceedings of the 39th Annual Computer Security Applications Conference, 14-28, 2023 | | 2023 |
| Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection K Greshake, S Abdelnabi, S Mishra, C Endres, T Holz, M Fritz Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security …, 2023 | 167 | 2023 |
| Certifiers Make Neural Networks Vulnerable to Availability Attacks T Lorenz, M Kwiatkowska, M Fritz Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security …, 2023 | 1 | 2023 |
| Client-specific property inference against secure aggregation in federated learning R Kerkouche, G Ács, M Fritz Proceedings of the 22nd Workshop on Privacy in the Electronic Society, 45-60, 2023 | 4 | 2023 |
