Anshuman Suri | Security Research Group

Reassessing EMNLP 2024’s Best Paper: Does Divergence-Based Calibration for Membership Inference Attacks Hold Up?

26 November 2024 David Evans, Anshuman Suri, privacy, membership inference, distribution inference, LLM

Anshuman Suri and Pratyush Maini wrote a blog about the EMNLP 2024 best paper award winner: Reassessing EMNLP 2024’s Best Paper: Does Divergence-Based Calibration for Membership Inference Attacks Hold Up?. As we explored in Do Membership Inference Attacks Work on Large Language Models?, to test a membership inference attack it is essentail to have a candidate set where the members and non-members are from the same distribution. If the distributions are different, the ability of an attack to distinguish members and non-members is indicative of distribution inference, not necessarily membership inference.

Common Way To Test for Leaks in Large Language Models May Be Flawed

13 November 2024 David Evans, Anshuman Suri, privacy, membership inference, distribution inference, LLM

UVA News has an article on our LLM membership inference work: Common Way To Test for Leaks in Large Language Models May Be Flawed: UVA Researchers Collaborated To Study the Effectiveness of Membership Inference Attacks, Eric Williamson, 13 November 2024.

Congratulations, Dr. Suri!

18 July 2024 Anshuman Suri, privacy, adversarial machine learning, membership inference, distribution inference, privacy-preserving machine learning, PhD defense, Alina Oprea

Congratulations to Anshuman Suri for successfully defending his PhD thesis! Tianhao Wang, Dr. Anshuman Suri, Nando Fioretto, Cong Shen On Screen: David Evans, Giuseppe Ateniese Inference Privacy in Machine Learning Using machine learning models comes at the risk of leaking information about data used in their training and deployment. This leakage can expose sensitive information about properties of the underlying data distribution, data from participating users, or even individual records in the training data.

SaTML Talk: SoK: Pitfalls in Evaluating Black-Box Attacks

22 April 2024 Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans, SaTML, adversarial machine learning, black-box adversarial attacks, systemization of knowledge

Anshuman Suri’s talk at IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) is now available:

See the earlier blog post for more on the work, and the paper at https://arxiv.org/abs/2310.17534.

Do Membership Inference Attacks Work on Large Language Models?

5 March 2024 Anshuman Suri, adversarial machine learning, privacy-preserving machine learning, distribution inference, inference privacy, LLMs, Michael Duan, Niloofar Mireshghallah, Sewon Min, Weijia Shi, Luke Zettlemoyer, Yulia Tsvetkov, Yejin Choi, Hannaneh Hajishirzi

MIMIR logo. Image credit: GPT-4 + DALL-E Paper Code Data Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model’s training data. Despite extensive research on traditional machine learning models, there has been limited work studying MIA on the pre-training data of large language models (LLMs). We perform a large-scale evaluation of MIAs over a suite of language models (LMs) trained on the Pile, ranging from 160M to 12B parameters.

SoK: Pitfalls in Evaluating Black-Box Attacks

20 December 2023 Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans, SaTML, adversarial machine learning, black-box adversarial attacks, systemization of knowledge

Post by Anshuman Suri and Fnu Suya Much research has studied black-box attacks on image classifiers, where adversaries generate adversarial examples against unknown target models without having access to their internal information. Our analysis of over 164 attacks (published in 102 major security, machine learning and security conferences) shows how these works make different assumptions about the adversary’s knowledge. The current literature lacks cohesive organization centered around the threat model. Our SoK paper (to appear at IEEE SaTML 2024) introduces a taxonomy for systematizing these attacks and demonstrates the importance of careful evaluations that consider adversary resources and threat models.

SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning

26 May 2023 Ahmed Salem, Anshuman Suri, Giovanni Cherubin, Boris Köpf, Andrew Paverd, Shruti Tople, Santiago Zanella-Béguelin, adversarial machine learning, privacy-preserving machine learning, membership inference, inference privacy

Our paper on the use of cryptographic-style games to model inference privacy is published in IEEE Symposium on Security and Privacy (Oakland):

Giovanni Cherubin, , Boris Köpf, Andrew Paverd, Anshuman Suri, Shruti Tople, and Santiago Zanella-Béguelin. SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning. IEEE Symposium on Security and Privacy, 2023. [Arxiv]

Tired of diverse definitions of machine learning privacy risks? Curious about game-based definitions? In our paper, we present privacy games as a tool for describing and analyzing privacy risks in machine learning. Join us on May 22nd, 11 AM @IEEESSP '23 https://t.co/NbRuTmHyd2 pic.twitter.com/CIzsT7UY4b
— ahmed salem (@AhmedGaSalem) May 15, 2023

CVPR 2023: Manipulating Transfer Learning for Property Inference

2 May 2023 Yulong Tian, Anshuman Suri, Fnu Suya, adversarial machine learning, privacy-preserving machine learning, distribution inference, inference privacy, transfer learning

Manipulating Transfer Learning for Property Inference Transfer learning is a popular method to train deep learning models efficiently. By reusing parameters from upstream pre-trained models, the downstream trainer can use fewer computing resources to train downstream models, compared to training models from scratch. The figure below shows the typical process of transfer learning for vision tasks: However, the nature of transfer learning can be exploited by a malicious upstream trainer, leading to severe risks to the downstream trainer.

MICO Challenge in Membership Inference

10 February 2023 adversarial machine learning, Anshuman Suri, privacy-preserving machine learning, membership inference

Anshuman Suri wrote up an interesting post on his experience with the MICO Challenge, a membership inference competition that was part of SaTML. Anshuman placed second in the competition (on the CIFAR data set), where the metric is highest true positive rate at a 0.1 false positive rate over a set of models (some trained using differential privacy and some without). Anshuman’s post describes the methods he used and his experience in the competition: My submission to the MICO Challenge.

Dissecting Distribution Inference

16 December 2022 property inference, distribution inference, Anshuman Suri, Yifu Lu, Yanjin Chen, privacy-preserving machine learning

(Cross-post by Anshuman Suri) Distribution inference attacks aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, as we demonstrated in previous work. KL Divergence Attack Most attacks against distribution inference involve training a meta-classifier, either using model parameters in white-box settings (Ganju et al., Property Inference Attacks on Fully Connected Neural Networks using Permutation Invariant Representations, CCS 2018), or using model predictions in black-box scenarios (Zhang et al.

All Posts by Category or Tags.