Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Khlaaf, Heidy"'
Discussions regarding the dual use of foundation models and the risks they pose have overwhelmingly focused on a narrow set of use cases and national security directives-in particular, how AI may enable the efficient construction of a class of system
Externí odkaz:
http://arxiv.org/abs/2410.14831
Autor:
Sorensen, Tyler, Khlaaf, Heidy
This paper describes LeftoverLocals: a vulnerability that allows data recovery from GPU memory created by another process on Apple, Qualcomm, and AMD GPUs. LeftoverLocals impacts the security posture of GPU applications, with particular significance
Externí odkaz:
http://arxiv.org/abs/2401.16603
Codex, a large language model (LLM) trained on a variety of codebases, exceeds the previous state of the art in its capacity to synthesize and generate code. Although Codex provides a plethora of benefits, models that may generate code on such scale
Externí odkaz:
http://arxiv.org/abs/2207.14157
Autor:
Chen, Mark, Tworek, Jerry, Jun, Heewoo, Yuan, Qiming, Pinto, Henrique Ponde de Oliveira, Kaplan, Jared, Edwards, Harri, Burda, Yuri, Joseph, Nicholas, Brockman, Greg, Ray, Alex, Puri, Raul, Krueger, Gretchen, Petrov, Michael, Khlaaf, Heidy, Sastry, Girish, Mishkin, Pamela, Chan, Brooke, Gray, Scott, Ryder, Nick, Pavlov, Mikhail, Power, Alethea, Kaiser, Lukasz, Bavarian, Mohammad, Winter, Clemens, Tillet, Philippe, Such, Felipe Petroski, Cummings, Dave, Plappert, Matthias, Chantzis, Fotios, Barnes, Elizabeth, Herbert-Voss, Ariel, Guss, William Hebgen, Nichol, Alex, Paino, Alex, Tezak, Nikolas, Tang, Jie, Babuschkin, Igor, Balaji, Suchir, Jain, Shantanu, Saunders, William, Hesse, Christopher, Carr, Andrew N., Leike, Jan, Achiam, Josh, Misra, Vedant, Morikawa, Evan, Radford, Alec, Knight, Matthew, Brundage, Miles, Murati, Mira, Mayer, Katie, Welinder, Peter, McGrew, Bob, Amodei, Dario, McCandlish, Sam, Sutskever, Ilya, Zaremba, Wojciech
We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex powers GitHub Copilot. On HumanEval, a new evaluation set we release to
Externí odkaz:
http://arxiv.org/abs/2107.03374
This report documents safety assurance argument templates to support the deployment and operation of autonomous systems that include machine learning (ML) components. The document presents example safety argument templates covering: the development o
Externí odkaz:
http://arxiv.org/abs/2102.02625
Autor:
Brundage, Miles, Avin, Shahar, Wang, Jasmine, Belfield, Haydn, Krueger, Gretchen, Hadfield, Gillian, Khlaaf, Heidy, Yang, Jingying, Toner, Helen, Fong, Ruth, Maharaj, Tegan, Koh, Pang Wei, Hooker, Sara, Leung, Jade, Trask, Andrew, Bluemke, Emma, Lebensold, Jonathan, O'Keefe, Cullen, Koren, Mark, Ryffel, Théo, Rubinovitz, JB, Besiroglu, Tamay, Carugati, Federica, Clark, Jack, Eckersley, Peter, de Haas, Sarah, Johnson, Maritza, Laurie, Ben, Ingerman, Alex, Krawczuk, Igor, Askell, Amanda, Cammarota, Rosario, Lohn, Andrew, Krueger, David, Stix, Charlotte, Henderson, Peter, Graham, Logan, Prunkl, Carina, Martin, Bianca, Seger, Elizabeth, Zilberman, Noa, hÉigeartaigh, Seán Ó, Kroeger, Frens, Sastry, Girish, Kagan, Rebecca, Weller, Adrian, Tse, Brian, Barnes, Elizabeth, Dafoe, Allan, Scharre, Paul, Herbert-Voss, Ariel, Rasser, Martijn, Sodhani, Shagun, Flynn, Carrick, Gilbert, Thomas Krendl, Dyer, Lisa, Khan, Saif, Bengio, Yoshua, Anderljung, Markus
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsibl
Externí odkaz:
http://arxiv.org/abs/2004.07213
Autor:
Bloomfield, Robin, Fletcher, Gareth, Khlaaf, Heidy, Ryan, Philippa, Kinoshita, Shuji, Kinoshit, Yoshiki, Takeyama, Makoto, Matsubara, Yutaka, Popov, Peter, Imai, Kazuki, Tsutake, Yoshinori
This report provides an introduction and overview of the Technical Topic Notes (TTNs) produced in the Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS (Tigars) project. These notes aim to support the development and evalu
Externí odkaz:
http://arxiv.org/abs/2003.00789
Autor:
Bloomfield, Robin, Fletcher, Gareth, Khlaaf, Heidy, Ryan, Philippa, Kinoshita, Shuji, Kinoshit, Yoshiki, Takeyama, Makoto, Matsubara, Yutaka, Popov, Peter, Imai, Kazuki, Tsutake, Yoshinori
This report provides an introduction and overview of the Technical Topic Notes (TTNs) produced in the Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS (Tigars) project. These notes aim to support the development and evalu
Externí odkaz:
http://arxiv.org/abs/2003.00790
Autor:
Khlaaf, Heidy
Software systems are increasingly present in every aspect of our society, as their deployment can be witnessed from seemingly trivial applications of light switches, to critical control systems of nuclear facilities. In the context of critical system
Externí odkaz:
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.747558
We present the open-source tool T2, the first public release from the TERMINATOR project. T2 has been extended over the past decade to support automatic temporal-logic proving techniques and to handle a general class of user-provided liveness and saf
Externí odkaz:
http://arxiv.org/abs/1512.08689