Get started
Author

Saeed Mahloujifar

The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure
2019 · Mahloujifar, Saeed, Diochnos, Dimitrios I., et al. · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 94
PDF
Property Inference from Poisoning
2022 · Saeed Mahloujifar, Esha Ghosh, et al. · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · 62
Experimenting with Zero-Knowledge Proofs of Training
2023 · Sanjam Garg, Aarushi Goel, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 41
PDF
Is Private Learning Possible with Instance Encoding?
2021 · Nicholas Carlini, Samuel Deng, et al. · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · 33
ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking
2023 · Chong Xiang, Alexander Valtchanov, et al. · Proceedings - IEEE Symposium on Security and Privacy/Proceedings of the ... IEEE Symposium on Security and Privacy · 31
PDF
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
2022 · Tong Wu, Tianhao Wang, et al. · ACM Workshop on Artificial Intelligence and Security (AISec) · 29
PDF
Parameterizing Activation Functions for Adversarial Robustness
2022 · Sihui Dai, Saeed Mahloujifar, et al. · IEEE Security and Privacy Workshops (SPW) · 27
PDF
SecAlign: Defending Against Prompt Injection with Preference Optimization
2025 · Sizhe Chen, Arman Zharmagambetov, et al. · ACM SIGSAC Conference on Computer and Communications Security (CCS) · 25
Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
2021 · Tang, Xinyu, Mahloujifar, Saeed, et al. · arXiv (Cornell University) · 20
PDF
PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
2021 · Xiang, Chong, Mahloujifar, Saeed, et al. · arXiv (Cornell University) · 19
PDF
Blockwise p-Tampering Attacks on Cryptographic Primitives, Extractors, and Learners
2017 · Saeed Mahloujifar, Mohammad Mahmoody · Lecture notes in computer science · 19
Improving Adversarial Robustness Using Proxy Distributions.
2021 · Vikash Sehwag, Saeed Mahloujifar, et al. · arXiv (Cornell University) · 16
An Attack on InstaHide: Is Private Learning Possible with Instance Encoding?
2020 · Nicholas Carlini, Samuel Deng, et al. · arXiv (Cornell University) · 15
Publicly-Detectable Watermarking for Language Models
2025 · Jaiden Fairoze, Sanjam Garg, et al. · IACR Communications in Cryptology · 14
PDF
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
2021 · Panda, Ashwinee, Mahloujifar, Saeed, et al. · arXiv (Cornell University) · 12
PDF
Membership Inference on Word Embedding and Beyond
2021 · Mahloujifar, Saeed, Inan, Huseyin A., et al. · arXiv (Cornell University) · 12
PDF
The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure
2019 · Saeed Mahloujifar, Dimitrios I. Diochnos, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 12
Can Adversarially Robust Learning Leverage Computational Hardness?
2018 · Mahloujifar, Saeed, Mahmoody, Mohammad · arXiv (Cornell University) · 12
PDF
Computational Concentration of Measure: Optimal Bounds, Reductions, and More
2019 · Omid Etesami, Saeed Mahloujifar, et al. · Society for Industrial and Applied Mathematics eBooks · 11
PDF
Empirically Measuring Concentration: Fundamental Limits to Intrinsic Robustness
2019 · Mahloujifar, Saeed, Zhang, Xiao, et al. · Figshare · 11
Is Private Learning Possible with Instance Encoding?
2020 · Carlini, Nicholas, Deng, Samuel, et al. · arXiv (Cornell University) · 10
PDF
Machine Learning with Differentially Private Labels: Mechanisms and Frameworks
2022 · Xinyu Tang, Milad Nasr, et al. · Proceedings on Privacy Enhancing Technologies · 9
PDF
Universal Multi-Party Poisoning Attacks
2018 · Mahloujifar, Saeed, Mahmoody, Mohammad, et al. · arXiv (Cornell University) · 9
PDF
Bounding training data reconstruction in DP-SGD
2023 · Jamie Hayes, Borja Balle, et al. · neural information processing systems · 8
PDF
Lower Bounds for Adversarially Robust PAC Learning
2019 · Diochnos, Dimitrios I., Mahloujifar, Saeed, et al. · arXiv (Cornell University) · 8
PDF
Works count: 65
Citation count: 637
H-index: 14
I10-index: 21
Year
Topic
Type