default search action
Saeed Mahloujifar
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c37]Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar, Vikash Sehwag, Prateek Mittal:
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization. ICML 2024 - [c36]Parham Yassini, Khaled M. Diab, Saeed Mahloujifar, Mohamed Hefeeda:
Horus: Granular In-Network Task Scheduler for Cloud Datacenters. NSDI 2024: 1-22 - [i43]Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, Prateek Mittal:
Private Fine-tuning of Large Language Models with Zeroth-order Optimization. CoRR abs/2401.04343 (2024) - [i42]Shengyuan Hu, Saeed Mahloujifar, Virginia Smith, Kamalika Chaudhuri, Chuan Guo:
Privacy Amplification for the Gaussian Mechanism via Bounded Support. CoRR abs/2403.05598 (2024) - [i41]Kamalika Chaudhuri, Chuan Guo, Laurens van der Maaten, Saeed Mahloujifar, Mark Tygert:
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds. CoRR abs/2404.02866 (2024) - 2023
- [c35]Sanjam Garg, Aarushi Goel, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Guru-Vamsi Policharla, Mingyuan Wang:
Experimenting with Zero-Knowledge Proofs of Training. CCS 2023: 1880-1894 - [c34]Xiangyu Qi, Tinghao Xie, Yiming Li, Saeed Mahloujifar, Prateek Mittal:
Revisiting the Assumption of Latent Separability for Backdoor Defenses. ICLR 2023 - [c33]Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin-Yu Chen, Prateek Mittal:
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks. ICML 2023: 6760-6785 - [c32]Milad Nasr, Saeed Mahloujifar, Xinyu Tang, Prateek Mittal, Amir Houmansadr:
Effectively Using Public Data in Privacy Preserving Machine Learning. ICML 2023: 25718-25732 - [c31]Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal:
Uncovering Adversarial Risks of Test-Time Adaptation. ICML 2023: 37456-37495 - [c30]Jamie Hayes, Borja Balle, Saeed Mahloujifar:
Bounding training data reconstruction in DP-SGD. NeurIPS 2023 - [c29]Jiachen T. Wang, Saeed Mahloujifar, Tong Wu, Ruoxi Jia, Prateek Mittal:
A Randomized Approach to Tight Privacy Accounting. NeurIPS 2023 - [c28]Chong Xiang, Alexander Valtchanov, Saeed Mahloujifar, Prateek Mittal:
ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking. SP 2023: 1329-1347 - [c27]Xiangyu Qi, Tinghao Xie, Jiachen T. Wang, Tong Wu, Saeed Mahloujifar, Prateek Mittal:
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples. USENIX Security Symposium 2023: 1685-1702 - [i40]Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal:
Uncovering Adversarial Risks of Test-Time Adaptation. CoRR abs/2301.12576 (2023) - [i39]Jamie Hayes, Saeed Mahloujifar, Borja Balle:
Bounding Training Data Reconstruction in DP-SGD. CoRR abs/2302.07225 (2023) - [i38]Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin-Yu Chen, Prateek Mittal:
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks. CoRR abs/2302.10980 (2023) - [i37]Jiachen T. Wang, Saeed Mahloujifar, Tong Wu, Ruoxi Jia, Prateek Mittal:
A Randomized Approach for Tight Privacy Accounting. CoRR abs/2304.07927 (2023) - [i36]Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Publicly Detectable Watermarking for Language Models. CoRR abs/2310.18491 (2023) - [i35]Sanjam Garg, Aarushi Goel, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Guru-Vamsi Policharla, Mingyuan Wang:
Experimenting with Zero-Knowledge Proofs of Training. IACR Cryptol. ePrint Arch. 2023: 1345 (2023) - [i34]Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Publicly Detectable Watermarking for Language Models. IACR Cryptol. ePrint Arch. 2023: 1661 (2023) - 2022
- [j2]Xinyu Tang, Milad Nasr, Saeed Mahloujifar, Virat Shejwalkar, Liwei Song, Amir Houmansadr, Prateek Mittal:
Machine Learning with Differentially Private Labels: Mechanisms and Frameworks. Proc. Priv. Enhancing Technol. 2022(4): 332-350 (2022) - [c26]Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal:
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification. AISTATS 2022: 7587-7624 - [c25]Tong Wu, Tianhao Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal:
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation. AISec@CCS 2022: 91-102 - [c24]Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang, Mung Chiang, Prateek Mittal:
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness? ICLR 2022 - [c23]Sihui Dai, Saeed Mahloujifar, Prateek Mittal:
Formulating Robustness Against Unforeseen Attacks. NeurIPS 2022 - [c22]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Overparameterization from Computational Constraints. NeurIPS 2022 - [c21]Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang, Ruoxi Jia, Prateek Mittal:
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning. NeurIPS 2022 - [c20]Sihui Dai, Saeed Mahloujifar, Prateek Mittal:
Parameterizing Activation Functions for Adversarial Robustness. SP (Workshops) 2022: 80-87 - [c19]Saeed Mahloujifar, Esha Ghosh, Melissa Chase:
Property Inference from Poisoning. SP 2022: 1120-1137 - [c18]Xinyu Tang, Saeed Mahloujifar, Liwei Song, Virat Shejwalkar, Milad Nasr, Amir Houmansadr, Prateek Mittal:
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture. USENIX Security Symposium 2022: 1433-1450 - [c17]Chong Xiang, Saeed Mahloujifar, Prateek Mittal:
PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier. USENIX Security Symposium 2022: 2065-2082 - [i33]Chong Xiang, Alexander Valtchanov, Saeed Mahloujifar, Prateek Mittal:
ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking. CoRR abs/2202.01811 (2022) - [i32]Saeed Mahloujifar, Alexandre Sablayrolles, Graham Cormode, Somesh Jha:
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms. CoRR abs/2204.06106 (2022) - [i31]Sihui Dai, Saeed Mahloujifar, Prateek Mittal:
Formulating Robustness Against Unforeseen Attacks. CoRR abs/2204.13779 (2022) - [i30]Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal:
Circumventing Backdoor Defenses That Are Based on Latent Separability. CoRR abs/2205.13613 (2022) - [i29]Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal:
Fight Poison with Poison: Detecting Backdoor Poison Samples via Decoupling Benign Correlations. CoRR abs/2205.13616 (2022) - [i28]Tong Wu, Tianhao Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal:
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation. CoRR abs/2207.10825 (2022) - [i27]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang:
Overparameterized (robust) models from computational constraints. CoRR abs/2208.12926 (2022) - [i26]Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang, Ruoxi Jia, Prateek Mittal:
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning. CoRR abs/2209.07716 (2022) - [i25]Ashwinee Panda, Xinyu Tang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal:
DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning. CoRR abs/2212.04486 (2022) - 2021
- [c16]Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, Yuan Tian:
Model-Targeted Poisoning Attacks with Provable Convergence. ICML 2021: 10000-10010 - [c15]Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Guha Thakurta:
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks. NeurIPS 2021: 10862-10875 - [c14]Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta, Florian Tramèr:
Is Private Learning Possible with Instance Encoding? SP 2021: 410-427 - [c13]Omid Etesami, Ji Gao, Saeed Mahloujifar, Mohammad Mahmoody:
Polynomial-Time Targeted Attacks on Coin Tossing for Any Number of Corruptions. TCC (2) 2021: 718-750 - [i24]Melissa Chase, Esha Ghosh, Saeed Mahloujifar:
Property Inference From Poisoning. CoRR abs/2101.11073 (2021) - [i23]Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang, Mung Chiang, Prateek Mittal:
Improving Adversarial Robustness Using Proxy Distributions. CoRR abs/2104.09425 (2021) - [i22]Saeed Mahloujifar, Huseyin A. Inan, Melissa Chase, Esha Ghosh, Marcello Hasegawa:
Membership Inference on Word Embedding and Beyond. CoRR abs/2106.11384 (2021) - [i21]Nicholas Carlini, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Florian Tramèr:
NeuraCrypt is not private. CoRR abs/2108.07256 (2021) - [i20]Chong Xiang, Saeed Mahloujifar, Prateek Mittal:
PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier. CoRR abs/2108.09135 (2021) - [i19]Sihui Dai, Saeed Mahloujifar, Prateek Mittal:
Parameterizing Activation Functions for Adversarial Robustness. CoRR abs/2110.05626 (2021) - [i18]Xinyu Tang, Saeed Mahloujifar, Liwei Song, Virat Shejwalkar, Milad Nasr, Amir Houmansadr, Prateek Mittal:
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture. CoRR abs/2110.08324 (2021) - [i17]Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal:
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification. CoRR abs/2112.06274 (2021) - [i16]Melissa Chase, Esha Ghosh, Saeed Mahloujifar:
Property Inference from Poisoning. IACR Cryptol. ePrint Arch. 2021: 99 (2021) - [i15]Omid Etesami, Ji Gao, Saeed Mahloujifar, Mohammad Mahmoody:
Polynomial-time targeted attacks on coin tossing for any number of corruptions. IACR Cryptol. ePrint Arch. 2021: 1464 (2021) - 2020
- [j1]Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody:
Learning under p-tampering poisoning attacks. Ann. Math. Artif. Intell. 88(7): 759-792 (2020) - [c12]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody:
Adversarially Robust Learning Could Leverage Computational Hardness. ALT 2020: 364-385 - [c11]Dimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody:
Lower Bounds for Adversarially Robust PAC Learning under Evasion and Hybrid Attacks. ICMLA 2020: 717-722 - [c10]Dimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody:
Lower Bounds for Adversarially Robust PAC Learning. ISAIM 2020 - [c9]Omid Etesami, Saeed Mahloujifar, Mohammad Mahmoody:
Computational Concentration of Measure: Optimal Bounds, Reductions, and More. SODA 2020: 345-363 - [i14]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta:
Obliviousness Makes Poisoning Adversaries Weaker. CoRR abs/2003.12020 (2020) - [i13]Fnu Suya, Saeed Mahloujifar, David Evans, Yuan Tian:
Model-Targeted Poisoning Attacks: Provable Convergence and Certified Bounds. CoRR abs/2006.16469 (2020) - [i12]Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramèr:
An Attack on InstaHide: Is Private Learning Possible with Instance Encoding? CoRR abs/2011.05315 (2020)
2010 – 2019
- 2019
- [c8]Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody:
The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure. AAAI 2019: 4536-4543 - [c7]Saeed Mahloujifar, Mohammad Mahmoody:
Can Adversarially Robust Learning LeverageComputational Hardness? ALT 2019: 581-609 - [c6]Saeed Mahloujifar, Mohammad Mahmoody, Ameer Mohammed:
Data Poisoning Attacks in Multi-Party Learning. ICML 2019: 4274-4283 - [c5]Saeed Mahloujifar, Xiao Zhang, Mohammad Mahmoody, David Evans:
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness. NeurIPS 2019: 5210-5221 - [i11]Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody:
Adversarially Robust Learning Could Leverage Computational Hardness. CoRR abs/1905.11564 (2019) - [i10]Saeed Mahloujifar, Xiao Zhang, Mohammad Mahmoody, David Evans:
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness. CoRR abs/1905.12202 (2019) - [i9]Dimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody:
Lower Bounds for Adversarially Robust PAC Learning. CoRR abs/1906.05815 (2019) - [i8]Omid Etesami, Saeed Mahloujifar, Mohammad Mahmoody:
Computational Concentration of Measure: Optimal Bounds, Reductions, and More. CoRR abs/1907.05401 (2019) - 2018
- [c4]Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody:
Learning under $p$-Tampering Attacks. ALT 2018: 572-596 - [c3]Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody:
Learning under p-Tampering Attacks. ISAIM 2018 - [c2]Dimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody:
Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution. NeurIPS 2018: 10380-10389 - [i7]Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody:
The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure. CoRR abs/1809.03063 (2018) - [i6]Saeed Mahloujifar, Mohammad Mahmoody, Ameer Mohammed:
Multi-party Poisoning through Generalized p-Tampering. CoRR abs/1809.03474 (2018) - [i5]Saeed Mahloujifar, Mohammad Mahmoody:
Can Adversarially Robust Learning Leverage Computational Hardness? CoRR abs/1810.01407 (2018) - [i4]Dimitrios I. Diochnos, Saeed Mahloujifar, Mohammad Mahmoody:
Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution. CoRR abs/1810.12272 (2018) - [i3]Saeed Mahloujifar, Mohammad Mahmoody, Ameer Mohammed:
Multi-party Poisoning through Generalized p-Tampering. IACR Cryptol. ePrint Arch. 2018: 854 (2018) - 2017
- [c1]Saeed Mahloujifar, Mohammad Mahmoody:
Blockwise p-Tampering Attacks on Cryptographic Primitives, Extractors, and Learners. TCC (2) 2017: 245-279 - [i2]Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody:
Learning under p-Tampering Attacks. CoRR abs/1711.03707 (2017) - [i1]Saeed Mahloujifar, Mohammad Mahmoody:
Blockwise p-Tampering Attacks on Cryptographic Primitives, Extractors, and Learners. IACR Cryptol. ePrint Arch. 2017: 950 (2017)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from , , and to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-04 20:01 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint