Zobrazeno 1 - 10
of 1 116
pro vyhledávání: '"Béguelin, A."'
Autor:
Siddiqui, Shoaib Ahmed, Gaonkar, Radhika, Köpf, Boris, Krueger, David, Paverd, Andrew, Salem, Ahmed, Tople, Shruti, Wutschitz, Lukas, Xia, Menglin, Zanella-Béguelin, Santiago
Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from one component can change the model's behavior and compromise the entire
Externí odkaz:
http://arxiv.org/abs/2410.03055
Autor:
Debenedetti, Edoardo, Rando, Javier, Paleka, Daniel, Florin, Silaghi Fineas, Albastroiu, Dragos, Cohen, Niv, Lemberg, Yuval, Ghosh, Reshmi, Wen, Rui, Salem, Ahmed, Cherubin, Giovanni, Zanella-Beguelin, Santiago, Schmid, Robin, Klemm, Victor, Miki, Takahiro, Li, Chenhao, Kraft, Stefan, Fritz, Mario, Tramèr, Florian, Abdelnabi, Sahar, Schönherr, Lea
Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaT
Externí odkaz:
http://arxiv.org/abs/2406.07954
Autor:
Cherubin, Giovanni, Köpf, Boris, Paverd, Andrew, Tople, Shruti, Wutschitz, Lukas, Zanella-Béguelin, Santiago
Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an $(\varepsilon,\delta)$-D
Externí odkaz:
http://arxiv.org/abs/2402.14397
Autor:
Vianne R. Gao, Rui Yang, Arnav Das, Renhe Luo, Hanzhi Luo, Dylan R. McNally, Ioannis Karagiannidis, Martin A. Rivas, Zhong-Min Wang, Darko Barisic, Alireza Karbalayghareh, Wilfred Wong, Yingqian A. Zhan, Christopher R. Chin, William S. Noble, Jeff A. Bilmes, Effie Apostolou, Michael G. Kharas, Wendy Béguelin, Aaron D. Viny, Danwei Huangfu, Alexander Y. Rudensky, Ari M. Melnick, Christina S. Leslie
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-15 (2024)
Abstract Identifying cell-type-specific 3D chromatin interactions between regulatory elements can help decipher gene regulation and interpret disease-associated non-coding variants. However, achieving this resolution with current 3D genomics technolo
Externí odkaz:
https://doaj.org/article/9058f5eecd4a4599ae65bc3feace0303
Autor:
Tobaben, Marlon, Shysheya, Aliaksandra, Bronskill, John, Paverd, Andrew, Tople, Shruti, Zanella-Beguelin, Santiago, Turner, Richard E, Honkela, Antti
Publikováno v:
Transactions on Machine Learning Research, ISSN 2835-8856, 2023
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are typically pretrained on large public datasets and then fine-tuned on pri
Externí odkaz:
http://arxiv.org/abs/2302.01190
Autor:
Lukas, Nils, Salem, Ahmed, Sim, Robert, Tople, Shruti, Wutschitz, Lukas, Zanella-Béguelin, Santiago
Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has received less at
Externí odkaz:
http://arxiv.org/abs/2302.00539
Autor:
Salem, Ahmed, Cherubin, Giovanni, Evans, David, Köpf, Boris, Paverd, Andrew, Suri, Anshuman, Tople, Shruti, Zanella-Béguelin, Santiago
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to reconstruction att
Externí odkaz:
http://arxiv.org/abs/2212.10986
Autor:
Jie Li, Christopher R. Chin, Hsia-Yuan Ying, Cem Meydan, Matthew R. Teater, Min Xia, Pedro Farinha, Katsuyoshi Takata, Chi-Shuen Chu, Yiyue Jiang, Jenna Eagles, Verena Passerini, Zhanyun Tang, Martin A. Rivas, Oliver Weigert, Trevor J. Pugh, Amy Chadburn, Christian Steidl, David W. Scott, Robert G. Roeder, Christopher E. Mason, Roberta Zappasodi, Wendy Béguelin, Ari M. Melnick
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-22 (2024)
Abstract Despite regulating overlapping gene enhancers and pathways, CREBBP and KMT2D mutations recurrently co-occur in germinal center (GC) B cell-derived lymphomas, suggesting potential oncogenic cooperation. Herein, we report that combined haploin
Externí odkaz:
https://doaj.org/article/a274f96f577b412184a054e29a28c213
Autor:
Zanella-Béguelin, Santiago, Wutschitz, Lukas, Tople, Shruti, Salem, Ahmed, Rühle, Victor, Paverd, Andrew, Naseri, Mohammad, Köpf, Boris, Jones, Daniel
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they afford in pr
Externí odkaz:
http://arxiv.org/abs/2206.05199
Autor:
Victoria Béguelin-Argimón
Publikováno v:
Cuadernos del CEMYR, Vol 32, Pp 27-44 (2024)
En tres reescrituras de algunos pasajes de la Collatio Alexandri cum Dindimo per litteras facta, contenidas respectivamente en el Libro de los ejemplos por a.b.c., el Cancionero d’Herberay des Essarts y el Libro de las maravillas del mundo de Mande
Externí odkaz:
https://doaj.org/article/43c9b28da1854dd084eadca4711c812e