| Open problems and fundamental limitations of reinforcement learning from human feedback S Casper, X Davies, C Shi, TK Gilbert, J Scheurer, J Rando, R Freedman, ... arXiv preprint arXiv:2307.15217, 2023 | 397 | 2023 |
| Red-Teaming the Stable Diffusion Safety Filter J Rando, D Paleka, D Lindner, L Heim, F Tramèr ML Safety Workshop - NeurIPS 2022, 2022 | 142 | 2022 |
| Foundational challenges in assuring alignment and safety of large language models U Anwar, A Saparov, J Rando, D Paleka, M Turpin, P Hase, ES Lubana, ... arXiv preprint arXiv:2404.09932, 2024 | 84 | 2024 |
| Scalable and transferable black-box jailbreaks for language models via persona modulation R Shah, S Pour, A Tagade, S Casper, J Rando arXiv preprint arXiv:2311.03348, 2023 | 74 | 2023 |
| Universal jailbreak backdoors from poisoned human feedback J Rando, F Tramèr arXiv preprint arXiv:2311.14455, 2023 | 45 | 2023 |
| "That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks E Mosca, S Agarwal, J Rando-Ramirez, G Groh ACL 2022, 2022 | 28 | 2022 |
| Personas as a Way to Model Truthfulness in Language Models N Joshi, J Rando, A Saparov, N Kim, H He arXiv preprint arXiv:2310.18168, 2023 | 20 | 2023 |
| PassGPT: password modeling and (guided) generation with large language models J Rando, F Perez-Cruz, B Hitaj European Symposium on Research in Computer Security, 164-183, 2023 | 16 | 2023 |
| Competition report: Finding universal jailbreak backdoors in aligned llms J Rando, F Croce, K Mitka, S Shabalin, M Andriushchenko, N Flammarion, ... arXiv preprint arXiv:2404.14461, 2024 | 15* | 2024 |
| Attributions toward artificial agents in a modified Moral Turing Test E Aharoni, S Fernandes, DJ Brady, C Alexander, M Criner, K Queen, ... Scientific Reports 14 (1), 8458, 2024 | 12 | 2024 |
| Uneven coverage of natural disasters in Wikipedia: The case of flood V Lorini, J Rando, D Saez-Trumper, C Castillo ISCRAM 2020, 2020 | 11 | 2020 |
| An adversarial perspective on machine unlearning for ai safety J Łucki, B Wei, Y Huang, P Henderson, F Tramèr, J Rando arXiv preprint arXiv:2409.18025, 2024 | 9* | 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 | 7 | 2024 |
| Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI R Hönig, J Rando, N Carlini, F Tramèr arXiv preprint arXiv:2406.12027, 2024 | 5 | 2024 |
| Gradient-based jailbreak images for multimodal fusion models J Rando, H Korevaar, E Brinkman, I Evtimov, F Tramèr arXiv preprint arXiv:2410.03489, 2024 | 1 | 2024 |
| Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO J Rando, N Naimi, T Baumann, M Mathys AdvML Frontiers Workshop (ICML 2022), 2022 | 1 | 2022 |
| Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations J Chi, U Karn, H Zhan, E Smith, J Rando, Y Zhang, K Plawiak, ZD Coudert, ... arXiv preprint arXiv:2411.10414, 2024 | | 2024 |
| Measuring Non-Adversarial Reproduction of Training Data in Large Language Models M Aerni, J Rando, E Debenedetti, N Carlini, D Ippolito, F Tramèr arXiv preprint arXiv:2411.10242, 2024 | | 2024 |
| Persistent Pre-Training Poisoning of LLMs Y Zhang, J Rando, I Evtimov, J Chi, EM Smith, N Carlini, F Tramèr, ... arXiv preprint arXiv:2410.13722, 2024 | | 2024 |
Florian TramèrAssistant Professor of Computer Science, ETH ZurichVerified email at inf.ethz.ch
