I agree that this site is using cookies. You can find further informations here.
X
Mahloujifar, Saeed
45  results:
Search for persons X
?
1

ObjectSeeker: Certifiably Robust Object Detection against P..:

, In: 2023 IEEE Symposium on Security and Privacy (SP),
Xiang, Chong ; Valtchanov, Alexander ; Mahloujifar, Saeed. - p. 1329-1347 , 2023
Link: https://doi.org/10.1109/..
 
?
2

Experimenting with Zero-Knowledge Proofs of Training:

, In: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security,
Garg, Sanjam ; Goel, Aarushi ; Jha, Somesh... - p. 1880-1894 , 2023
Link: https://dl.acm.org/doi/1..
 
?
3

Property Inference from Poisoning:

, In: 2022 IEEE Symposium on Security and Privacy (SP),
Mahloujifar, Saeed ; Ghosh, Esha ; Chase, Melissa - p. 1120-1137 , 2022
Link: https://doi.org/10.1109/..
 
?
4

Machine Learning with Differentially Private Labels: Mechan..:

Tang, Xinyu ; Nasr, Milad ; Mahloujifar, Saeed...
Proceedings on Privacy Enhancing Technologies.  2022 (2022)  4 - p. 332-350 , 2022
Link: https://doi.org/10.56553..
 
?
5

Just Rotate it: Deploying Backdoor Attacks via Rotation Tra..:

, In: Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security,
Wu, Tong ; Wang, Tianhao ; Sehwag, Vikash.. - p. 91-102 , 2022
Link: https://dl.acm.org/doi/1..
 
?
6

Parameterizing Activation Functions for Adversarial Robustn..:

, In: 2022 IEEE Security and Privacy Workshops (SPW),
Dai, Sihui ; Mahloujifar, Saeed ; Mittal, Prateek - p. 80-87 , 2022
Link: https://doi.org/10.1109/..
 
?
7

Is Private Learning Possible with Instance Encoding?:

, In: 2021 IEEE Symposium on Security and Privacy (SP),
Carlini, Nicholas ; Deng, Samuel ; Garg, Sanjam... - p. 410-427 , 2021
Link: https://doi.org/10.1109/..
 
?
8

Polynomial-Time Targeted Attacks on Coin Tossing for Any Nu..:

, In: Theory of Cryptography; Lecture Notes in Computer Science,
Etesami, Omid ; Gao, Ji ; Mahloujifar, Saeed. - p. 718-750 , 2021
Link: https://doi.org/10.1007/..
 
?
9

Computational concentration of measure : optimal bounds,..:

, In: Proceedings of the Thirty-First Annual ACM-SIAM Symposium on Discrete Algorithms,
Etesami, Omid ; Mahloujifar, Saeed ; Mahmoody, Mohammad - p. 345-363 , 2020
Link: https://dl.acm.org/doi/1..
 
?
10

Learning under p-tampering poisoning attacks:

Mahloujifar, Saeed ; Diochnos, Dimitrios I. ; Mahmoody, Mohammad
Annals of Mathematics and Artificial Intelligence.  88 (2019)  7 - p. 759-792 , 2019
Link: https://doi.org/10.1007/..
 
?
11

Private Fine-tuning of Large Language Models with Zeroth-or..:

Tang, Xinyu ; Panda, Ashwinee ; Nasr, Milad..
http://arxiv.org/abs/2401.04343.  , 2024
Link: http://arxiv.org/abs/240..
 
?
12

Uncovering Adversarial Risks of Test-Time Adaptation:

Wu, Tong ; Jia, Feiran ; Qi, Xiangyu...
http://arxiv.org/abs/2301.12576.  , 2023
Link: http://arxiv.org/abs/230..
 
?
13

MultiRobustBench: Benchmarking Robustness Against Multiple ..:

Dai, Sihui ; Mahloujifar, Saeed ; Xiang, Chong...
http://arxiv.org/abs/2302.10980.  , 2023
Link: http://arxiv.org/abs/230..
 
?
14

Publicly Detectable Watermarking for Language Models:

Fairoze, Jaiden ; Garg, Sanjam ; Jha, Somesh...
http://arxiv.org/abs/2310.18491.  , 2023
Link: http://arxiv.org/abs/231..
 
?
15

A Randomized Approach for Tight Privacy Accounting:

Wang, Jiachen T ; Mahloujifar, Saeed ; Wu, Tong..
http://arxiv.org/abs/2304.07927.  , 2023
Link: http://arxiv.org/abs/230..
 
1-15