Robust physical-world attacks on deep learning visual classification K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, C Xiao, A Prakash, ... Proceedings of the IEEE conference on computer vision and pattern …, 2018 | 3291* | 2018 |
Code llama: Open foundation models for code B Roziere, J Gehring, F Gloeckle, S Sootla, I Gat, XE Tan, Y Adi, J Liu, ... arXiv preprint arXiv:2308.12950, 2023 | 1409 | 2023 |
The llama 3 herd of models A Dubey, A Jauhri, A Pandey, A Kadian, A Al-Dahle, A Letman, A Mathur, ... arXiv preprint arXiv:2407.21783, 2024 | 1317 | 2024 |
Physical adversarial examples for object detectors D Song, K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, F Tramer, ... 12th USENIX workshop on offensive technologies (WOOT 18), 2018 | 587 | 2018 |
Seamless: Multilingual Expressive and Streaming Speech Translation L Barrault, YA Chung, MC Meglioli, D Dale, N Dong, M Duppenthaler, ... arXiv preprint arXiv:2312.05187, 2023 | 85 | 2023 |
The llama 3 herd of models, 2024 A Dubey, A Jauhri, A Pandey, A Kadian, A Al-Dahle, A Letman, A Mathur, ... URL https://arxiv. org/abs/2407.21783 2407, 21783, 0 | 75 | |
Purple llama cyberseceval: A secure coding benchmark for language models M Bhatt, S Chennabasappa, C Nikolaidis, S Wan, I Evtimov, D Gabi, ... arXiv preprint arXiv:2312.04724, 2023 | 53 | 2023 |
A whac-a-mole dilemma: Shortcuts come in multiples where mitigating one amplifies others Z Li, I Evtimov, A Gordo, C Hazirbas, T Hassner, CC Ferrer, C Xu, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 53 | 2023 |
Imagenet-x: Understanding model mistakes with factor of variation annotations BY Idrissi, D Bouchacourt, R Balestriero, I Evtimov, C Hazirbas, N Ballas, ... arXiv preprint arXiv:2211.01866, 2022 | 42 | 2022 |
Is tricking a robot hacking? I Evtimov, D O’Hair, E Fernandes, R Calo, T Kohno Berkeley Technology Law Journal 34 (3), 891-918, 2019 | 35* | 2019 |
FoggySight: A Scheme for Facial Lookup Privacy I Evtimov, P Sturmfels, T Kohno Proceedings on Privacy Enhancing Technologies 2021 (3), 204-226, 2021 | 29 | 2021 |
Robust physical-world attacks on deep learning visual classification K Eykholt, I Evtimov, E Fernandes, B Li, A Rahmati, C Xiao, A Prakash, ... | 21 | 2020 |
Security and machine learning in the real world I Evtimov, W Cui, E Kamar, E Kiciman, T Kohno, J Li arXiv preprint arXiv:2007.07205, 2020 | 19 | 2020 |
You only need a good embeddings extractor to fix spurious correlations R Mehta, V Albiero, L Chen, I Evtimov, T Glaser, Z Li, T Hassner arXiv preprint arXiv:2212.06254, 2022 | 16 | 2022 |
Disrupting model training with adversarial shortcuts I Evtimov, I Covert, A Kusupati, T Kohno arXiv preprint arXiv:2106.06654, 2021 | 9 | 2021 |
Adversarial evaluation of multimodal models under realistic gray box assumption I Evtimov, R Howes, B Dolhansky, H Firooz, CC Ferrer arXiv preprint arXiv:2011.12902, 2020 | 9 | 2020 |
Vpa: Fully test-time visual prompt adaptation J Sun, M Ibrahim, M Hall, I Evtimov, ZM Mao, CC Ferrer, C Hazirbas Proceedings of the 31st ACM International Conference on Multimedia, 5796-5806, 2023 | 7 | 2023 |
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations C Tomani, K Chaudhuri, I Evtimov, D Cremers, M Ibrahim arXiv preprint arXiv:2404.10960, 2024 | 3 | 2024 |
Adversarial text normalization J Bitton, M Pavlova, I Evtimov arXiv preprint arXiv:2206.04137, 2022 | 3 | 2022 |
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 |