arXiv subjects

Anwar Hithnawi

Publications and source records attributed to Anwar Hithnawi.

17 recordsLinked to original sources

arXiv2026

Atlas: Efficient Verifiable Semantic Search

Semantic search is a core primitive of modern applications, powering recommender systems, web search, and retrieval-augmented generation for language models. The provider controls the index and query execution, leaving clients to trust that results come from the right algorithm over the intended index. A provider may truncate search to cut cost, bias results, or otherwise deviate from the specified execution undetected. Verifiability can remove this trust assumption by proving that results follow the agreed algorithm over a committed index. Realizing this efficiently is hard, as retrieval at scale relies on HNSW, a graph-based algorithm whose data-dependent traversal maps poorly onto the fixed constraint systems of zero-knowledge proofs. Prior verifiable systems therefore target regular, cluster-based indices that are easier to encode, sacrificing the recall of graph-based search. We present Atlas, a system that lets a provider prove a query was answered correctly against its committed index without revealing the index. At its core is a new zero-knowledge proof for HNSW search, built on three techniques: preprocessing that shifts all database-dependent cost offline, so per-query proving scales with the traversal rather than the database; a restructuring of HNSW into a fixed-size-state procedure that we prove returns the same result; and a timestep-tagged batching that merges the per-step arguments of the entire traversal into one. Atlas is the first to demonstrate verifiable graph-based search at scale, proving a query in under a second on the SIFT1M benchmark and in 2.0 seconds at 100 million vectors, while maintaining the recall of plaintext HNSW and revealing nothing about the index beyond the result. In a complete RAG pipeline, Atlas' proven retrieval preserves end-to-end answer quality, and reaches higher quality at lower proving cost than all prior verifiable retrieval systems.

cs.CR↗

arXiv2026

Enhancing Privacy, Neglecting Harms: An Analysis of Real-World Digital Privacy Incidents

Privacy-enhancing technologies (PETs) have emerged as a technical means for providing individuals with greater control over their information. Yet despite the growing deployment of PETs, people continue to experience privacy harms. In this work, we revisit our understanding of privacy incidents and the realities of those experiencing privacy harms, to assess whether the goals and abilities of PETs are misaligned with the harms people face. For our study, we collect news articles that correspond to a sample of 257 real-world privacy incidents. We employ content analysis over the articles to develop a new information flow model that encompasses the complexity of data flows and their relation to resulting harms. We demonstrate that our model captures both established and novel aspects of privacy incidents and their mitigations. In particular, it captures why consent is often insufficient to prevent privacy violations, how harms emerge from complex interactions among multiple entities and actions, and reveals a flaw in our understanding of PETs: a focus on enabling functionalities still permits the harms inherent in those functionalities. Moreover, we find that the entities best positioned to implement harm-preventing measures for the incidents in our sample are the least incentivized to do so. Overall, our model and analysis identify limitations of privacy technology research for harm prevention and further identifies paths for transforming how we approach the advancement of these technologies.

cs.CR↗

arXiv2025

DPolicy: Managing Privacy Risks Across Multiple Releases with Differential Privacy

Differential Privacy (DP) has emerged as a robust framework for privacy-preserving data releases and has been successfully applied in high-profile cases, such as the 2020 US Census. However, in organizational settings, the use of DP remains largely confined to isolated data releases. This approach restricts the potential of DP to serve as a framework for comprehensive privacy risk management at an organizational level. Although one might expect that the cumulative privacy risk of isolated releases could be assessed using DP's compositional property, in practice, individual DP guarantees are frequently tailored to specific releases, making it difficult to reason about their interaction or combined impact. At the same time, less tailored DP guarantees, which compose more easily, also offer only limited insight because they lead to excessively large privacy budgets that convey limited meaning. To address these limitations, we present DPolicy, a system designed to manage cumulative privacy risks across multiple data releases using DP. Unlike traditional approaches that treat each release in isolation or rely on a single (global) DP guarantee, our system employs a flexible framework that considers multiple DP guarantees simultaneously, reflecting the diverse contexts and scopes typical of real-world DP deployments. DPolicy introduces a high-level policy language to formalize privacy guarantees, making traditionally implicit assumptions on scopes and contexts explicit. By deriving the DP guarantees required to enforce complex privacy semantics from these high-level policies, DPolicy enables fine-grained privacy risk management on an organizational scale. We implement and evaluate DPolicy, demonstrating how it mitigates privacy risks that can emerge without comprehensive, organization-wide privacy risk management.

cs.CR↗

arXiv2024

Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks

As machine learning models become increasingly complex, concerns about their robustness and trustworthiness have become more pressing. A critical vulnerability of these models is data poisoning attacks, where adversaries deliberately alter training data to degrade model performance. One particularly stealthy form of these attacks is subpopulation poisoning, which targets distinct subgroups within a dataset while leaving overall performance largely intact. The ability of these attacks to generalize within subpopulations poses a significant risk in real-world settings, as they can be exploited to harm marginalized or underrepresented groups within the dataset. In this work, we investigate how model complexity influences susceptibility to subpopulation poisoning attacks. We introduce a theoretical framework that explains how overparameterized models, due to their large capacity, can inadvertently memorize and misclassify targeted subpopulations. To validate our theory, we conduct extensive experiments on large-scale image and text datasets using popular model architectures. Our results show a clear trend: models with more parameters are significantly more vulnerable to subpopulation poisoning. Moreover, we find that attacks on smaller, human-interpretable subgroups often go undetected by these models. These results highlight the need to develop defenses that specifically address subpopulation vulnerabilities.

cs.LG↗

arXiv2024

UTrace: Poisoning Forensics for Private Collaborative Learning

Privacy-preserving machine learning (PPML) systems enable multiple data owners to collaboratively train models without revealing their raw, sensitive data by leveraging cryptographic protocols such as secure multi-party computation (MPC). While PPML offers strong privacy guarantees, it also introduces new attack surfaces: malicious data owners can inject poisoned data into the training process without being detected, thus undermining the integrity of the learned model. Although recent defenses, such as private input validation within MPC, can mitigate some specific poisoning strategies, they remain insufficient, particularly in preventing stealthy or distributed attacks. As the robustness of PPML remains an open challenge, strengthening trust in these systems increasingly necessitates post-hoc auditing mechanisms that instill accountability. In this paper we present UTrace, a framework for user-level traceback in PPML that attributes integrity failures to responsible data owners without compromising the privacy guarantees of MPC. UTrace encapsulates two mechanisms: a gradient similarity method that identifies suspicious update patterns linked to poisoning, and a user-level unlearning technique that quantifies each user's marginal influence on model behavior. Together, these methods allow UTrace to attribute model misbehavior to specific users with high precision. We implement UTrace within an MPC-compatible training and auditing pipeline and evaluate its effectiveness on four datasets spanning vision, text, and malware. Across ten canonical poisoning attacks, UTrace consistently achieves high detection accuracy with low false positive rates.

cs.CR↗

arXiv2024

Artemis: Efficient Commit-and-Prove SNARKs for zkML

Ensuring that AI models are both verifiable and privacy-preserving is important for trust, accountability, and compliance. To address these concerns, recent research has focused on developing zero-knowledge machine learning (zkML) techniques that enable the verification of various aspects of ML models without revealing sensitive information. However, while recent zkML advances have made significant improvements to the efficiency of proving ML computations, they have largely overlooked the costly consistency checks on committed model parameters and input data, which have become a dominant performance bottleneck. To address this gap, this paper introduces a new Commit-and-Prove SNARK (CP-SNARK) construction, Artemis, that effectively addresses the emerging challenge of commitment verification in zkML pipelines. In contrast to existing approaches, Artemis is compatible with any homomorphic polynomial commitment, including those without trusted setup. We present the first implementation of this CP-SNARK, evaluate its performance on a diverse set of ML models, and show substantial improvements over existing methods, achieving significant reductions in prover costs and maintaining efficiency even for large-scale models. For example, for the VGG model, we reduce the overhead associated with commitment checks from 11.5x to 1.1x. Our results indicate that Artemis provides a concrete step toward practical deployment of zkML, particularly in settings involving large-scale or complex models.

cs.CR↗

arXiv2024

Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning

Recent advancements in privacy-preserving machine learning are paving the way to extend the benefits of ML to highly sensitive data that, until now, have been hard to utilize due to privacy concerns and regulatory constraints. Simultaneously, there is a growing emphasis on enhancing the transparency and accountability of machine learning, including the ability to audit ML deployments. While ML auditing and PPML have both been the subjects of intensive research, they have predominately been examined in isolation. However, their combination is becoming increasingly important. In this work, we introduce Arc, an MPC framework for auditing privacy-preserving machine learning. At the core of our framework is a new protocol for efficiently verifying MPC inputs against succinct commitments at scale. We evaluate the performance of our framework when instantiated with our consistency protocol and compare it to hashing-based and homomorphic-commitment-based approaches, demonstrating that it is up to 10^4x faster and up to 10^6x more concise.

cs.CR↗

arXiv2023

Cohere: Managing Differential Privacy in Large Scale Systems

The need for a privacy management layer in today's systems started to manifest with the emergence of new systems for privacy-preserving analytics and privacy compliance. As a result, many independent efforts have emerged that try to provide system support for privacy. Recently, the scope of privacy solutions used in systems has expanded to encompass more complex techniques such as Differential Privacy (DP). The use of these solutions in large-scale systems imposes new challenges and requirements. Careful planning and coordination are necessary to ensure that privacy guarantees are maintained across a wide range of heterogeneous applications and data systems. This requires new solutions for managing and allocating scarce and non-replenishable privacy resources. In this paper, we introduce Cohere, a new system that simplifies the use of DP in large-scale systems. Cohere implements a unified interface that allows heterogeneous applications to operate on a unified view of users' data. In this work, we further address two pressing system challenges that arise in the context of real-world deployments: ensuring the continuity of privacy-based applications (i.e., preventing privacy budget depletion) and effectively allocating scarce shared privacy resources (i.e., budget) under complex preferences. Our experiments show that Cohere achieves a 6.4--28x improvement in utility compared to the state-of-the-art across a range of complex workloads.

cs.CR↗

arXiv2023

Verifiable Fully Homomorphic Encryption

Fully Homomorphic Encryption (FHE) is seeing increasing real-world deployment to protect data in use by allowing computation over encrypted data. However, the same malleability that enables homomorphic computations also raises integrity issues, which have so far been mostly overlooked. While FHEs lack of integrity has obvious implications for correctness, it also has severe implications for confidentiality: a malicious server can leverage the lack of integrity to carry out interactive key-recovery attacks. As a result, virtually all FHE schemes and applications assume an honest-but-curious server who does not deviate from the protocol. In practice, however, this assumption is insufficient for a wide range of deployment scenarios. While there has been work that aims to address this gap, these have remained isolated efforts considering only aspects of the overall problem and fail to fully address the needs and characteristics of modern FHE schemes and applications. In this paper, we analyze existing FHE integrity approaches, present attacks that exploit gaps in prior work, and propose a new notion for maliciously-secure verifiable FHE. We then instantiate this new notion with a range of techniques, analyzing them and evaluating their performance in a range of different settings. We highlight their potential but also show where future work on tailored integrity solutions for FHE is still required.

cs.CR↗

arXiv2022

CoVault: A Secure Analytics Platform

Analytics on personal data, such as individuals' mobility, financial, and health data can be of significant benefit to society. Such data is already collected by smartphones, apps and services today, but liberal societies have so far refrained from making it available for large-scale analytics. Arguably, this is due at least in part to the lack of an analytics platform that can secure data through transparent, technical means (ideally with decentralized trust), enforce source policies, handle millions of distinct data sources, and run queries on billions of records with acceptable query latencies. To bridge this gap, we present an analytics platform called CoVault which combines secure multi-party computation (MPC) with trusted execution environment (TEE)-based delegation of trust to be able execute approved queries on encrypted data contributed by individuals within a datacenter to achieve the above properties. We show that CoVault scales well despite the high cost of MPC. For example, CoVault can process data relevant to epidemic analytics for a country of 80M people (about 11.85B data records/day) on a continuous basis using a core pair for every 20,000 people. Compared to a state-of-the-art MPC-based platform, CoVault can process queries between 7 to over 100 times faster, as well as scale to many sources and big data.

cs.CR↗

arXiv2022

HECO: Fully Homomorphic Encryption Compiler

In recent years, Fully Homomorphic Encryption (FHE) has undergone several breakthroughs and advancements, leading to a leap in performance. Today, performance is no longer a major barrier to adoption. Instead, it is the complexity of developing an efficient FHE application that currently limits deploying FHE in practice and at scale. Several FHE compilers have emerged recently to ease FHE development. However, none of these answer how to automatically transform imperative programs to secure and efficient FHE implementations. This is a fundamental issue that needs to be addressed before we can realistically expect broader use of FHE. Automating these transformations is challenging because the restrictive set of operations in FHE and their non-intuitive performance characteristics require programs to be drastically transformed to achieve efficiency. Moreover, existing tools are monolithic and focus on individual optimizations. Therefore, they fail to fully address the needs of end-to-end FHE development. In this paper, we present HECO, a new end-to-end design for FHE compilers that takes high-level imperative programs and emits efficient and secure FHE implementations. In our design, we take a broader view of FHE development, extending the scope of optimizations beyond the cryptographic challenges existing tools focus on.

cs.CR↗

arXiv2021

Zeph: Cryptographic Enforcement of End-to-End Data Privacy

As increasingly more sensitive data is being collected to gain valuable insights, the need to natively integrate privacy controls in data analytics frameworks is growing in importance. Today, privacy controls are enforced by data curators with full access to data in the clear. However, a plethora of recent data breaches show that even widely trusted service providers can be compromised. Additionally, there is no assurance that data processing and handling comply with the claimed privacy policies. This motivates the need for a new approach to data privacy that can provide strong assurance and control to users. This paper presents Zeph, a system that enables users to set privacy preferences on how their data can be shared and processed. Zeph enforces privacy policies cryptographically and ensures that data available to third-party applications complies with users' privacy policies. Zeph executes privacy-adhering data transformations in real-time and scales to thousands of data sources, allowing it to support large-scale low-latency data stream analytics. We introduce a hybrid cryptographic protocol for privacy-adhering transformations of encrypted data. We develop a prototype of Zeph on Apache Kafka to demonstrate that Zeph can perform large-scale privacy transformations with low overhead.

cs.CR↗

arXiv2021

RoFL: Robustness of Secure Federated Learning

Even though recent years have seen many attacks exposing severe vulnerabilities in Federated Learning (FL), a holistic understanding of what enables these attacks and how they can be mitigated effectively is still lacking. In this work, we demystify the inner workings of existing (targeted) attacks. We provide new insights into why these attacks are possible and why a definitive solution to FL robustness is challenging. We show that the need for ML algorithms to memorize tail data has significant implications for FL integrity. This phenomenon has largely been studied in the context of privacy; our analysis sheds light on its implications for ML integrity. We show that certain classes of severe attacks can be mitigated effectively by enforcing constraints such as norm bounds on clients' updates. We investigate how to efficiently incorporate these constraints into secure FL protocols in the single-server setting. Based on this, we propose RoFL, a new secure FL system that extends secure aggregation with privacy-preserving input validation. Specifically, RoFL can enforce constraints such as $L_2$ and $L_\infty$ bounds on high-dimensional encrypted model updates.

cs.CR↗

arXiv2021

SoK: Fully Homomorphic Encryption Compilers

Fully Homomorphic Encryption (FHE) allows a third party to perform arbitrary computations on encrypted data, learning neither the inputs nor the computation results. Hence, it provides resilience in situations where computations are carried out by an untrusted or potentially compromised party. This powerful concept was first conceived by Rivest et al. in the 1970s. However, it remained unrealized until Craig Gentry presented the first feasible FHE scheme in 2009. The advent of the massive collection of sensitive data in cloud services, coupled with a plague of data breaches, moved highly regulated businesses to increasingly demand confidential and secure computing solutions. This demand, in turn, has led to a recent surge in the development of FHE tools. To understand the landscape of recent FHE tool developments, we conduct an extensive survey and experimental evaluation to explore the current state of the art and identify areas for future development. In this paper, we survey, evaluate, and systematize FHE tools and compilers. We perform experiments to evaluate these tools' performance and usability aspects on a variety of applications. We conclude with recommendations for developers intending to develop FHE-based applications and a discussion on future directions for FHE tools development.

cs.CR↗

arXiv2018

TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control

A growing number of devices and services collect detailed time series data that is stored in the cloud. Protecting the confidentiality of this vast and continuously generated data is an acute need for many applications in this space. At the same time, we must preserve the utility of this data by enabling authorized services to securely and selectively access and run analytics. This paper presents TimeCrypt, a system that provides scalable and real-time analytics over large volumes of encrypted time series data. TimeCrypt allows users to define expressive data access and privacy policies and enforces it cryptographically via encryption. In TimeCrypt, data is encrypted end-to-end, and authorized parties can only decrypt and verify queries within their authorized access scope. Our evaluation of TimeCrypt shows that its memory overhead and performance are competitive and close to operating on data in the clear.

cs.CR↗

arXiv2018

Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams

This paper presents Droplet, a decentralized data access control service. Droplet enables data owners to securely and selectively share their encrypted data while guaranteeing data confidentiality in the presence of unauthorized parties and compromised data servers. Droplet's contribution lies in coupling two key ideas: (i) a cryptographically-enforced access control construction for encrypted data streams which enables users to define fine-grained stream-specific access policies, and (ii) a decentralized authorization service that serves user-defined access policies. In this paper, we present Droplet's design, the reference implementation of Droplet, and the experimental results of three case-study applications deployed with Droplet: Fitbit activity tracker, Ava health tracker, and ECOviz smart meter dashboard, demonstrating Droplet's applicability for secure sharing of IoT streams.

cs.CR↗

arXiv2017

Towards Blockchain-based Auditable Storage and Sharing of IoT Data

Today the cloud plays a central role in storing, processing, and distributing data. Despite contributing to the rapid development of IoT applications, the current IoT cloud-centric architecture has led into a myriad of isolated data silos that hinders the full potential of holistic data-driven analytics within the IoT. In this paper, we present a blockchain-based design for the IoT that brings a distributed access control and data management. We depart from the current trust model that delegates access control of our data to a centralized trusted authority and instead empower the users with data ownership. Our design is tailored for IoT data streams and enables secure data sharing. We enable a secure and resilient access control management, by utilizing the blockchain as an auditable and distributed access control layer to the storage layer. We facilitate the storage of time-series IoT data at the edge of the network via a locality-aware decentralized storage system that is managed with the blockchain technology. Our system is agnostic of the physical storage nodes and supports as well utilization of cloud storage resources as storage nodes.

cs.DC↗