Search dblp for Publications

export results for "Are aligned neural networks adversarially aligned?"

 download as .bib file

@inproceedings{DBLP:conf/nips/CarliniNCJGKITS23,
  author       = {Nicholas Carlini and
                  Milad Nasr and
                  Christopher A. Choquette{-}Choo and
                  Matthew Jagielski and
                  Irena Gao and
                  Pang Wei Koh and
                  Daphne Ippolito and
                  Florian Tram{\`{e}}r and
                  Ludwig Schmidt},
  editor       = {Alice Oh and
                  Tristan Naumann and
                  Amir Globerson and
                  Kate Saenko and
                  Moritz Hardt and
                  Sergey Levine},
  title        = {Are aligned neural networks adversarially aligned?},
  booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference
                  on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
                  LA, USA, December 10 - 16, 2023},
  year         = {2023},
  url          = {http://papers.nips.cc/paper\_files/paper/2023/hash/c1f0b856a35986348ab3414177266f75-Abstract-Conference.html},
  timestamp    = {Fri, 01 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/CarliniNCJGKITS23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-15447,
  author       = {Nicholas Carlini and
                  Milad Nasr and
                  Christopher A. Choquette{-}Choo and
                  Matthew Jagielski and
                  Irena Gao and
                  Anas Awadalla and
                  Pang Wei Koh and
                  Daphne Ippolito and
                  Katherine Lee and
                  Florian Tram{\`{e}}r and
                  Ludwig Schmidt},
  title        = {Are aligned neural networks adversarially aligned?},
  journal      = {CoRR},
  volume       = {abs/2306.15447},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.15447},
  doi          = {10.48550/ARXIV.2306.15447},
  eprinttype    = {arXiv},
  eprint       = {2306.15447},
  timestamp    = {Fri, 30 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-15447.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}