Ich stimme zu, dass diese Seite Cookies verwende. Weitere Informationen finden Sie unter unseren Datenschutzerklärungen .
X
Mireshghallah, FatemehSadat
33  Ergebnisse:
OpenAccess-Volltexte X
Personensuche X
?
1

Privacy-Preserving In-Context Learning with Differentially ..:

Tang, Xinyu ; Shin, Richard ; Inan, Huseyin A...
http://arxiv.org/abs/2309.11765.  , 2023
Link: http://arxiv.org/abs/230..
 
?
2

Membership Inference Attacks against Language Models via Ne..:

Mattern, Justus ; Mireshghallah, Fatemehsadat ; Jin, Zhijing...
http://arxiv.org/abs/2305.18462.  , 2023
Link: http://arxiv.org/abs/230..
 
?
3

Smaller Language Models are Better Black-box Machine-Genera..:

Mireshghallah, Fatemehsadat ; Mattern, Justus ; Gao, Sicun..
http://arxiv.org/abs/2305.09859.  , 2023
Link: http://arxiv.org/abs/230..
 
?
4

Membership Inference Attacks against Language Models via Ne..:

Mattern, Justus ; Mireshghallah, Fatemehsadat ; Jin, Zhijing...
info:eu-repo/semantics/altIdentifier/doi/10.18653/v1/2023.findings-acl.719.  , 2023
Link: https://hdl.handle.net/2..
 
?
5

Auditing and Mitigating Safety Risks in Large Language Mode..:

Mireshghallah, Fatemehsadat
qt28f9b6px.  , 2023
Link: https://escholarship.org..
 
?
6

Are Chatbots Ready for Privacy-Sensitive Applications? An I..:

Priyanshu, Aman ; Vijay, Supriti ; Kumar, Ayush..
http://arxiv.org/abs/2305.15008.  , 2023
Link: http://arxiv.org/abs/230..
 
?
7

LatticeGen: A Cooperative Framework which Hides Generated T..:

Zhang, Mengke ; He, Tianxing ; Wang, Tianle...
http://arxiv.org/abs/2309.17157.  , 2023
Link: http://arxiv.org/abs/230..
 
?
8

Non-Parametric Temporal Adaptation for Social Media Topic C..:

Mireshghallah, Fatemehsadat ; Vogler, Nikolai ; He, Junxian...
http://arxiv.org/abs/2209.05706.  , 2022
Link: http://arxiv.org/abs/220..
 
?
9

FLUTE: A Scalable, Extensible Framework for High-Performanc..:

Garcia, Mirian Hipolito ; Manoel, Andre ; Diaz, Daniel Madrigal...
http://arxiv.org/abs/2203.13789.  , 2022
Link: http://arxiv.org/abs/220..
 
?
10

Mix and Match: Learning-free Controllable Text Generation u..:

Mireshghallah, Fatemehsadat ; Goyal, Kartik ; Berg-Kirkpatrick, Taylor
http://arxiv.org/abs/2203.13299.  , 2022
Link: http://arxiv.org/abs/220..
 
?
11

Quantifying Privacy Risks of Masked Language Models Using M..:

Mireshghallah, Fatemehsadat ; Goyal, Kartik ; Uniyal, Archit..
http://arxiv.org/abs/2203.03929.  , 2022
Link: http://arxiv.org/abs/220..
 
?
12

Differentially Private Model Compression:

Mireshghallah, Fatemehsadat ; Backurs, Arturs ; Inan, Huseyin A..
http://arxiv.org/abs/2206.01838.  , 2022
Link: http://arxiv.org/abs/220..
 
?
13

Memorization in NLP Fine-tuning Methods:

Mireshghallah, Fatemehsadat ; Uniyal, Archit ; Wang, Tianhao..
http://arxiv.org/abs/2205.12506.  , 2022
Link: http://arxiv.org/abs/220..
 
?
14

Privacy-Preserving Domain Adaptation of Semantic Parsers:

Mireshghallah, Fatemehsadat ; Su, Yu ; Hashimoto, Tatsunori..
http://arxiv.org/abs/2212.10520.  , 2022
Link: http://arxiv.org/abs/221..
 
?
15

What Does it Mean for a Language Model to Preserve Privacy?:

Brown, Hannah ; Lee, Katherine ; Mireshghallah, Fatemehsadat..
http://arxiv.org/abs/2202.05520.  , 2022
Link: http://arxiv.org/abs/220..
 
1-15