ABCDEFGHIJKLMNOPQRSTUVWXYZ
1
Presenter Name
2
Privacy Attacks against Machine Learning
3
4
1. [Reconstructing Training Data with Informed Adversaries](https://arxiv.org/pdf/2201.04845.pdf)Zoraiz Qureshi
5
2. [Extracting Training Data from Large Language Models](https://www.usenix.org/system/files/sec21-carlini-extracting.pdf)Md Khairul Islam
6
3. [Property Inference Attacks on Fully Connected Neural Networks using Permutation Invariant Representations](https://dl.acm.org/doi/pdf/10.1145/3243734.3243834)Xiamei Zhang
7
4. [Counterfactual Memorization in Neural Language Models](https://arxiv.org/pdf/2112.12938)Zetian Liu
8
5. [Formalizing and Estimating Distribution Inference Risks](https://arxiv.org/pdf/2109.06024.pdf)Black Wang
9
6. [Enhanced Membership Inference Attacks against Machine Learning Models](https://arxiv.org/pdf/2111.09679.pdf)
10
7. [Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture](https://arxiv.org/pdf/2110.08324.pdf)
11
8. [Is Private Learning Possible with Instance Encoding?](https://arxiv.org/pdf/2011.05315.pdf)Arthur Harris
12
9. [Submix: Practical Private Prediction For Large-scale Language Models](https://arxiv.org/pdf/2201.00971.pdf)Shuhao Tian
13
10. [Composition Attacks and Auxiliary Information in Data Privacy](https://arxiv.org/pdf/0803.0032)Qinglin Li
14
11. [StolenEncoder: Stealing Pre-trained Encoders](https://arxiv.org/pdf/2201.05889.pdf)
15
16
Machine Learning Security (Instead of Privacy)
17
18
12. [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://www.usenix.org/system/files/sec20summer_fang_prepub.pdf)Xinyue Fan
19
13. [Spinning Language Models for Propaganda-As-A-Service](https://arxiv.org/pdf/2112.05224.pdf)Siddharth Ghatti
20
14. [Blind Backdoors in Deep Learning Models](https://arxiv.org/pdf/2005.03823.pdf)Meng Wang
21
22
Differential Privacy Theory
23
24
15. [Renyi Differential Privacy](https://arxiv.org/pdf/1702.07476.pdf)
25
16. [Numerical Composition of Differential Privacy](https://arxiv.org/pdf/2106.02848.pdf)Charlie DiLorenzo
26
17. [Differentially Private Combinatorial Optimization](https://epubs.siam.org/doi/pdf/10.1137/1.9781611973075.90)
27
18. [Iterative Constructions and Private Data Release](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.649.1598&rep=rep1&type=pdf)
28
19. [On the Rényi Differential Privacy of the Shuffle Model](https://dl.acm.org/doi/pdf/10.1145/3460120.3484794)
29
30
Differential Privacy for Machine Learning
31
32
20. [Scalable Private Learning With PATE](https://arxiv.org/pdf/1802.08908.pdf)Abdolrasoul Sharifi
33
21. [DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy](https://arxiv.org/pdf/2110.08557.pdf)Xin Liu
34
22. [Hyperparameter Tuning with Renyi Differential Privacy](https://arxiv.org/pdf/2110.03620.pdf)
35
23. [Benchmarking Differential Privacy and Federated Learning for BERT Models](https://arxiv.org/pdf/2106.13973.pdf)Yuchen Lin
36
24. [Public Data-Assisted Mirror Descent for Private Model Training](https://arxiv.org/pdf/2112.00193)Zhengkun Xiao
37
25. [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://arxiv.org/pdf/2101.04535.pdf)Hongyu Xiang
38
26. [The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection](https://arxiv.org/pdf/2111.04906)Ziao Yu
39
27. [Differentially private fine-tuning of language models](https://arxiv.org/pdf/2110.06500)Fan Liu
40
28. [Large language models can be strong differentially private learners](https://arxiv.org/pdf/2110.05679)Andrew Wang
41
29. [Large Scale Private Learning via Low-rank Reparametrization](https://arxiv.org/pdf/2106.09352.pdf)Yunli liu
42
43
Differential Privacy and Cryptography
44
45
30. [Strengthening Order Preserving Encryption with Differential Privacy](https://arxiv.org/pdf/2009.05679.pdf)
46
31. [Shrinkwrap: Efficient SQL Query Processing in Differentially Private Data Federations](https://par.nsf.gov/servlets/purl/10223658)Xinzhu Zhang
47
32. [Differentially Private Oblivious RAM](https://arxiv.org/pdf/1601.03378.pdf)Bingxue Xie
48
49
Privacy and Systems
50
51
33. [Veil: Private Browsing Semantics Without Browser-side Assistance](https://frankwang.org/files/papers/wang-veil.pdf)Siyou Wang
52
34. [εpsolute: Efficiently Querying Databases While Providing Differential Privacy](https://arxiv.org/pdf/1706.01552.pdf)Kishorekarthick
53
35. [Packet scheduling with optional client privacy](https://www.cis.upenn.edu/~sga001/papers/ifs-ccs21.pdf)Linyang Du
54
36. [Data Privacy in Trigger-Action Systems](https://pages.cs.wisc.edu/~yc/assets/pdf/etap.pdf)Jiechao Gao
55
37. [εKTELO A Framework for Defining Differentially Private Computations](https://dl.acm.org/doi/pdf/10.1145/3362032)
56
38. [PrivateSQL: a differentially private SQL query engine](http://www.vldb.org/pvldb/vol12/p1371-kotsogiannis.pdf)Wanghao Long
57
58
Other General Privacy
59
60
39. [Privacy Engineering Meets Software Engineering. On the Challenges of Engineering Privacy By Design](https://arxiv.org/pdf/2007.08613.pdf)
61
40. [Towards formalizing the GDPR’s notion of singling out](https://www.pnas.org/content/pnas/117/15/8344.full.pdf)Haoqian Li
62
41. [Differential privacy: An economic method for choosing epsilon](https://arxiv.org/pdf/1402.3329)
63
42. [Privacy Implications of Shuffling](https://arxiv.org/pdf/2106.06603.pdf)Shuhao Dong
64
43. [Causally Constrained Data Synthesis for Private Data Release](https://arxiv.org/pdf/2105.13144.pdf)Mingyue Tang
65
44. [DP-Sync: Hiding Update Patterns in Secure Outsourced Databases with Differential Privacy](https://arxiv.org/pdf/2103.15942.pdf)
66
45. [Kamino: Constraint-Aware Differentially Private Data Synthesis](http://vldb.org/pvldb/vol14/p1886-ge.pdf)
67
31
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100