PMPrateek Mittal

Prateek Mittal

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Prateek Mittal has a total of 186 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    QUICstep: Evaluating connection migration based QUIC censorship circumvention

    by Seungju Lee, Mona Wang, Watson Jia, Qiang Wu, Henry Birge-Lee, Liang Wang, Prateek Mittal

    Internet censors often rely on information in the first few packets of a connection to censor unwanted traffic. With the rise of the QUIC transport protocol, prior work has suggested the method of using QUIC connection migration to conceal the first few handshake packets using a different network path (e.g., an encrypted proxy channel). However, the use of connection migration for censorship circumvention has not been explored or validated in terms of feasibility or performance. We bridge this gap by providing a rigorous quantitative evaluation of this approach that we name QUICstep. We develop a lightweight, application-agnostic prototype of QUICstep and demonstrate that QUICstep is able to circumvent a real-world QUIC SNI censor. We find that not only does QUICstep outperform a fully encrypted channel in diverse settings, but also that it can significantly reduce traffic load for encrypted channel providers. We also propose using QUICstep as a tool for measuring QUIC connection migration support in the wild and show that support for connection migration is on the rise. While as of now QUIC and connection migration support is limited, we envision that QUICstep can be a useful tool for the future where QUIC is the de facto norm for the Internet.

  • Open Access

    A Framework to Evaluate MPIC Security using Real-World BGP Announcements

    by Henry Birge-Lee, Ari Brown, Christine Guo, Cyrill Krähenbühl, Sohom Pal, Liang Wang, Prateek Mittal

  • Open Access

    What WeChat Knows: Pervasive First-Party Tracking in a Billion-User Super-App Ecosystem

    by Mona Wang, Pellaeon Lin, Jeffrey Knockel, Will Greenberg, Jonathan Mayer, Prateek Mittal

    This work studies the analytics and first-party tracking ecosystem of WeChat Mini Programs. WeChat Mini Programs have almost one billion monthly active users, comprising one of the largest ap- plication and analytics ecosystems in the world. A key challenge in investigating the privacy of WeChat’s Mini Programs is WeChat’s use of a proprietary network encryption protocol, MMTLS, to trans- mit analytics data. First, we reverse-engineer WeChat’s network stack, and release tooling and specifications for investigating net- work requests sent to WeChat servers. Leveraging this tooling, we analyze the requests sent by 104 popular Mini Programs to perform the first characterization and analysis of WeChat’s user tracking across their Mini Program ecosystem. Overall, we identified fine- grained browsing data in 76.0% of the network traces we decrypted. This tracking including browsing and search queries performed within third-party Mini Programs, some of which manage particu- larly sensitive data; for instance, we also identified browsing data in 89.7% of the traces we decrypted from 40 health-related Mini Programs. We ultimately find that the first-party platform, WeChat, is comprehensively tracking user activity with third-party Mini Programs, at an unprecedented scale. There is no way for users nor Mini Program developers to opt-out of this data collection.


  • Open Access

    Scaling SCIERA: A Journey Through the Deployment of a Next-generation Network

    by François Wirz, Marten Gartner, Jelte van Bommel, Elham Ehsani Moghadam, Grace H. Cimaszewski, Anxiao He, Yizhe Zhang, Henry Birge-Lee, Felix Kottmann, Cyrill Krähenbühl, et al.


  • Open Access

    PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches

    by Dennis Jacob, Chong Xiang, Prateek Mittal

    Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically realizable nature of these attacks calls for certifiable defenses, which feature provable guarantees on robustness. While certifiable defenses have been successfully applied to single-label classification, limited work has been done for multi-label classification. In this work, we present PatchDEMUX, a certifiably robust framework for multi-label classifiers against adversarial patches. Our approach is a generalizable method which can extend any existing certifiable defense for single-label classification; this is done by considering the multi-label classification task as a series of isolated binary classification problems to provably guarantee robustness. Furthermore, in the scenario where an attacker is limited to a single patch we propose an additional certification procedure that can provide tighter robustness bounds. Using the current state-of-the-art (SOTA) single-label certifiable defense PatchCleanser as a backbone, we find that PatchDEMUX can achieve non-trivial robustness on the MS-COCO and PASCAL VOC datasets while maintaining high clean performance

  • Open Access

    Differentially Private Image Classification by Learning Priors from Random Processes

    by Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal

    In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A recent focus in private learning research is improving the performance of DP-SGD on private data by incorporating priors that are learned on real-world public data. In this work, we explore how we can improve the privacy-utility tradeoff of DP-SGD by learning priors from images generated by random processes and transferring these priors to private data. We propose DP-RandP, a three-phase approach. We attain new state-of-the-art accuracy when training from scratch on CIFAR10, CIFAR100, MedMNIST and ImageNet for a range of privacy budgets $\epsilon \in [1, 8]$. In particular, we improve the previous best reported accuracy on CIFAR10 from $60.6 \%$ to $72.3 \%$ for $\epsilon=1$.


  • Open Access

    On Evaluating the Durability of Safeguards for Open-Weight LLMs

    by Xiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson

    Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.

  • Top Cited Papers
    Open Access

    Visual Adversarial Examples Jailbreak Aligned Large Language Models

    by Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Peter Henderson, Mengdi Wang, Prateek Mittal

    Warning: this paper contains data, prompts, and model outputs that are offensive in nature. Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of this trend. First, we underscore that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks, representing an expanded attack surface of vision-integrated LLMs. Second, we highlight that the versatility of LLMs also presents visual attackers with a wider array of achievable adversarial objectives, extending the implications of security failures beyond mere misclassification. As an illustration, we present a case study in which we exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. Intriguingly, we discover that a single visual adversarial example can universally jailbreak an aligned LLM, compelling it to heed a wide range of harmful instructions (that it otherwise would not) and generate harmful content that transcends the narrow scope of a `few-shot' derogatory corpus initially employed to optimize the adversarial example. Our study underscores the escalating adversarial risks associated with the pursuit of multimodality. Our findings also connect the long-studied adversarial vulnerabilities of neural networks to the nascent field of AI alignment. The presented attack suggests a fundamental adversarial challenge for AI alignment, especially in light of the emerging trend toward multimodality in frontier foundation models.


  • Open Access

    Efficient Data Shapley for Weighted Nearest Neighbor Algorithms

    by Jiachen T. Wang, Prateek Mittal, Ruoxi Jia

    This work aims to address an open problem in data valuation literature concerning the efficient computation of Data Shapley for weighted $K$ nearest neighbor algorithm (WKNN-Shapley). By considering the accuracy of hard-label KNN with discretized weights as the utility function, we reframe the computation of WKNN-Shapley into a counting problem and introduce a quadratic-time algorithm, presenting a notable improvement from $O(N^K)$, the best result from existing literature. We develop a deterministic approximation algorithm that further improves computational efficiency while maintaining the key fairness properties of the Shapley value. Through extensive experiments, we demonstrate WKNN-Shapley's computational efficiency and its superior performance in discerning data quality compared to its unweighted counterpart.

  • Open Access

    Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker

    by Sihui Dai, Wenxin Ding, Arjun Nitin Bhagoji, Daniel Cullina, Ben Y. Zhao, Haitao Zheng, Prateek Mittal

    Finding classifiers robust to adversarial examples is critical for their safe deployment. Determining the robustness of the best possible classifier under a given threat model for a given data distribution and comparing it to that achieved by state-of-the-art training methods is thus an important diagnostic tool. In this paper, we find achievable information-theoretic lower bounds on loss in the presence of a test-time attacker for multi-class classifiers on any discrete dataset. We provide a general framework for finding the optimal 0-1 loss that revolves around the construction of a conflict hypergraph from the data and adversarial constraints. We further define other variants of the attacker-classifier game that determine the range of the optimal loss more efficiently than the full-fledged hypergraph construction. Our evaluation shows, for the first time, an analysis of the gap to optimal robustness for classifiers in the multi-class setting on benchmark datasets.