Open sesame! universal black box jailbreaking of large language models R Lapid, R Langberg, M Sipper SeT LLM @ ICLR 2024, 2023 | 56 | 2023 |
An evolutionary, gradient-free, query-efficient, black-box algorithm for generating adversarial instances in deep convolutional neural networks R Lapid, Z Haramaty, M Sipper Algorithms @ MDPI 2022, 2022 | 15 | 2022 |
Evolution of Activation Functions for Deep Learning-Based Image Classification R Lapid, M Sipper NEWK @ GECCO 2022, 2022 | 15 | 2022 |
Foiling Explanations in Deep Neural Networks SV Tamam, R Lapid, M Sipper TMLR 2023, 2022 | 10 | 2022 |
I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Models R Lapid, M Sipper MLCS @ ECML-PKDD 2023, 2023 | 8 | 2023 |
Patch of invisibility: Naturalistic black-box adversarial attacks on object detectors R Lapid, E Mizrahi, M Sipper arXiv preprint arXiv:2303.04238, 2023 | 8 | 2023 |
Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors R Lapid, A Dubin, M Sipper arXiv preprint arXiv:2404.12120, 2024 | | 2024 |
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors B Pinhasov, R Lapid, R Ohayon, M Sipper, Y Aperstein arXiv preprint arXiv:2403.02955, 2024 | | 2024 |
What's in an AI's Mind's Eye? We Must Know M Sipper, R Lapid Authorea Preprints, 2024 | | 2024 |
A Melting Pot of Evolution and Learning M Sipper, A Elyasaf, T Halperin, Z Haramaty, R Lapid, E Segal, I Tzruia, ... GPTP 2023, 2023 | | 2023 |