2024 Do Parameters Reveal More than Loss for Membership Inference? Anshuman Suri, Xiao Zhang, and David Evans Transactions on Machine Learning Research (TMLR), 2024 Bib PDF Code @article{suri2024do, title = {Do Parameters Reveal More than Loss for Membership Inference?}, author = {Suri, Anshuman and Zhang, Xiao and Evans, David}, journal = {Transactions on Machine Learning Research (TMLR)}, year = {2024}, url = {https://arxiv.org/abs/2406.11544}, } Do Membership Inference Attacks Work on Large Language Models? Michael Duan*, Anshuman Suri*, Niloofar Mireshghallah, and 7 more authors In Conference on Language Modeling (COLM), 2024 Bib PDF Code Website @inproceedings{duan2024membership, title = {Do Membership Inference Attacks Work on Large Language Models?}, author = {Duan, Michael and Suri, Anshuman and Mireshghallah, Niloofar and Min, Sewon and Shi, Weijia and Zettlemoyer, Luke and Tsvetkov, Yulia and Choi, Yejin and Evans, David and Hajishirzi, Hannaneh}, year = {2024}, booktitle = {Conference on Language Modeling (COLM)}, } SoK: Pitfalls in Evaluating Black-Box Attacks Fnu Suya*, Anshuman Suri*, Tingwei Zhang, and 3 more authors In IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2024 Bib PDF Video Code @inproceedings{suya2024sok, title = {SoK: Pitfalls in Evaluating Black-Box Attacks}, author = {Suya, Fnu and Suri, Anshuman and Zhang, Tingwei and Hong, Jingtao and Tian, Yuan and Evans, David}, booktitle = {IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)}, year = {2024}, } 2023 SoK: Memorization in General-Purpose Large Language Models Valentin Hartmann, Anshuman Suri, Vincent Bindschaedler, and 3 more authors arXiv:2310.18362, 2023 Bib PDF @article{hartmann2023sok, title = {SoK: Memorization in General-Purpose Large Language Models}, author = {Hartmann, Valentin and Suri, Anshuman and Bindschaedler, Vincent and Evans, David and Tople, Shruti and West, Robert}, year = {2023}, journal = {arXiv:2310.18362}, } Manipulating Transfer Learning for Property Inference Yulong Tian, Fnu Suya, Anshuman Suri, and 2 more authors In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 Bib PDF Video Code @inproceedings{tian2023manipulating, title = {Manipulating Transfer Learning for Property Inference}, author = {Tian, Yulong and Suya, Fnu and Suri, Anshuman and Xu, Fengyuan and Evans, David}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, } SoK: Let The Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning Ahmed Salem, Giovanni Cherubin, David Evans, and 5 more authors IEEE Symposium on Security and Privacy (S&P), 2023 Bib PDF Video @article{salem2022sok, title = {{SoK}: Let The Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning}, author = {Salem, Ahmed and Cherubin, Giovanni and Evans, David and Köpf, Boris and Paverd, Andrew and Suri, Anshuman and Tople, Shruti and Zanella-Béguelin, Santiago}, journal = {IEEE Symposium on Security and Privacy (S&P)}, year = {2023}, } Dissecting Distribution Inference Anshuman Suri, Yifu Lu, Yanjin Chen, and 1 more author In IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2023 Bib PDF Video Code @inproceedings{suri2023dissecting, title = {Dissecting Distribution Inference}, author = {Suri, Anshuman and Lu, Yifu and Chen, Yanjin and Evans, David}, booktitle = {IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)}, year = {2023}, } 2022 Formalizing and Estimating Distribution Inference Risks Anshuman Suri, and David Evans Proceedings on Privacy Enhancing Technologies, 2022 Bib PDF Video Code @article{suri2022formalizing, title = {Formalizing and Estimating Distribution Inference Risks}, author = {Suri, Anshuman and Evans, David}, journal = {Proceedings on Privacy Enhancing Technologies}, year = {2022}, } Subject Membership Inference Attacks in Federated Learning Anshuman Suri, Pallika Kanani, Virendra J. Marathe, and 1 more author arXiv preprint arXiv:2206.03317, 2022 Bib PDF @article{suri2022subject, title = {Subject Membership Inference Attacks in Federated Learning}, author = {Suri, Anshuman and Kanani, Pallika and Marathe, Virendra J. and Peterson, Daniel W.}, journal = {arXiv preprint arXiv:2206.03317}, year = {2022}, } 2020 Model-Targeted Poisoning Attacks with Provable Convergence Fnu Suya, Saeed Mahloujifar, Anshuman Suri, and 2 more authors In International Conference on Machine Learning, 2020 Bib PDF Code @inproceedings{suya2020model, title = {Model-Targeted Poisoning Attacks with Provable Convergence}, author = {Suya, Fnu and Mahloujifar, Saeed and Suri, Anshuman and Evans, David and Tian, Yuan}, booktitle = {International Conference on Machine Learning}, year = {2020}, } QnAMaker: Data to Bot in 2 Minutes Parag Agrawal, Tulasi Menon, Aya Kam, and 8 more authors In Companion Proceedings of the Web Conference 2020, 2020 Bib PDF @inproceedings{agrawal2020qnamaker, title = {{QnAMaker}: Data to Bot in 2 Minutes}, author = {Agrawal, Parag and Menon, Tulasi and Kam, Aya and Naim, Michel and Chouragade, Chaikesh and Singh, Gurvinder and Kulkarni, Rohan and Suri, Anshuman and Katakam, Sahithi and Pratik, Vineet and others}, booktitle = {Companion Proceedings of the Web Conference 2020}, pages = {131--134}, year = {2020}, } One Neuron to Fool Them All Anshuman Suri, and David Evans arXiv preprint arXiv:2003.09372, 2020 Bib PDF Code @article{suri2020one, title = {One Neuron to Fool Them All}, author = {Suri, Anshuman and Evans, David}, journal = {arXiv preprint arXiv:2003.09372}, year = {2020}, } A2-LINK: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain Knowledge A. Suri, M. Vatsa, and R. Singh IEEE Transactions on Biometrics, Behavior, and Identity Science, 2020 Bib PDF Code @article{9104705, author = {{Suri}, A. and {Vatsa}, M. and {Singh}, R.}, journal = {IEEE Transactions on Biometrics, Behavior, and Identity Science}, title = {A2-{LINK}: Recognizing Disguised Faces via Active Learning and Adversarial Noise based Inter-Domain Knowledge}, year = {2020}, } 2019 Hardening Deep Neural Networks via Adversarial Model Cascades Deepak Vijaykeerthy, Anshuman Suri, Sameep Mehta, and 1 more author In 2019 International Joint Conference on Neural Networks (IJCNN), 2019 Bib PDF Code @inproceedings{vijaykeerthy2019hardening, title = {Hardening Deep Neural Networks via Adversarial Model Cascades}, author = {Vijaykeerthy, Deepak and Suri, Anshuman and Mehta, Sameep and Kumaraguru, Ponnurangam}, booktitle = {2019 International Joint Conference on Neural Networks (IJCNN)}, year = {2019}, organization = {IEEE}, } Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling Vighnesh Leonardo Shiv, Chris Quirk, Anshuman Suri, and 8 more authors In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 2019 Bib PDF Code @inproceedings{shiv2019microsoft, title = {Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling}, author = {Shiv, Vighnesh Leonardo and Quirk, Chris and Suri, Anshuman and Gao, Xiang and Shahid, Khuram and Govindarajan, Nithya and Zhang, Yizhe and Gao, Jianfeng and Galley, Michel and Brockett, Chris and others}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations}, pages = {123--128}, year = {2019}, } A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge Anshuman Suri, Mayank Vatsa, and Richa Singh In 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS), 2019 Bib PDF Code @inproceedings{suri2019link, title = {A-{LINK}: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge}, author = {Suri, Anshuman and Vatsa, Mayank and Singh, Richa}, booktitle = {2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS)}, pages = {1--8}, year = {2019}, organization = {IEEE}, } NELEC at SemEval-2019 Task 3: Think Twice Before Going Deep Parag Agrawal, and Anshuman Suri In Proceedings of the 13th International Workshop on Semantic Evaluation, 2019 Bib PDF @inproceedings{agrawal2019nelec, title = {{NELEC} at SemEval-2019 {T}ask 3: Think Twice Before Going Deep}, author = {Agrawal, Parag and Suri, Anshuman}, booktitle = {Proceedings of the 13th International Workshop on Semantic Evaluation}, pages = {266--271}, year = {2019}, } 2018 A Trustworthy, Responsible and Interpretable System to Handle Chit-Chat in Conversational Bots Parag Agrawal, Anshuman Suri, and Tulasi Menon In The Second AAAI Workshop on Reasoning and Learning for Human-Machine Dialogues, 2018 Bib PDF @inproceedings{agrawal2018a, author = {Agrawal, Parag and Suri, Anshuman and Menon, Tulasi}, title = {A Trustworthy, Responsible and Interpretable System to Handle Chit-Chat in Conversational Bots}, booktitle = {The Second AAAI Workshop on Reasoning and Learning for Human-Machine Dialogues}, year = {2018}, } 2017 Towards Understanding Crisis Events On Online Social Networks Through Pictures Prateek Dewan, Anshuman Suri, Varun Bharadhwaj, and 2 more authors In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, 2017 Bib PDF Code Website @inproceedings{dewan2017towards, title = {Towards Understanding Crisis Events On Online Social Networks Through Pictures}, author = {Dewan, Prateek and Suri, Anshuman and Bharadhwaj, Varun and Mithal, Aditi and Kumaraguru, Ponnurangam}, booktitle = {Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017}, year = {2017}, }