arXiv subjects

Rouzbeh Behnia

Publications and source records attributed to Rouzbeh Behnia.

At least 19 recordsLinked to original sources

arXiv2026

A Lightweight Post-Quantum Authentication Framework for 5G Base Station Bootstrapping

The absence of authenticated bootstrapping between User Equipments (UEs) and Base Stations (BSs) in 5G leaves System Information Block (SIB) broadcasts unprotected, enabling fake BS attacks, man-in-the-middle interception, and spoofed emergency alerts. Prior efforts such as Public Key Infrastructure (PKI)-based certificate chains, token-based schemes, and identity-based signatures either impose overhead exceeding 5G's strict packet-size constraints or lack post-quantum (PQ) security. Direct NIST-PQC integration is also infeasible; current standards, such as ML-DSA requires 34 fragmented SIB1 packets and up to 5,282\,ms end-to-end delay, and FN-DSA still requires 13 fragments and up to 1,920\,ms. We propose EMULSION, a symmetric chained publicly verifiable authentication framework for 5G/6G BS broadcast authentication. EMULSION is the first framework to exploit native 5G architectural features: fixed SIB transmission windows, millisecond-level time synchronization, and eSIM/USIM credential management to achieve genuine PQ security at symmetric-key efficiency. It uses a timed stream loss-tolerant authentication with HMAC chain anchored by a compact PQ signature~(MAYO) applied once per epoch, fitting authentication within a single packet with no fragmentation and eliminating certificate transmission entirely. Unlike prior schemes, EMULSION extends to the full SIB family (SIB1-SIB21) at no additional per-broadcast cost, demonstrated over the air on SIB1. Evaluated on a real over-the-air 5G testbed, EMULSION achieves 33x lower end-to-end delay and 31x less communication overhead than ML-DSA, and 12x lower delay and 5.4x less overhead than FN-DSA. We formally prove the security of EMULSION and open-source its implementation for public testing and adaptation.

cs.CR↗

arXiv2026

Information Theoretic Adversarial Training of Large Language Models

Large language models (LLMs) remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to scale. Recent continuous adversarial training methods, such as Continuous adversarial training (CAT) and Continuous Adversarial Preference Optimization (CAPO), address this challenge by leveraging gradient-based perturbations in the embedding space, enabling more efficient and expressive attacks. Building on this paradigm, we propose WARDEN, a distributionally robust adversarial training framework for LLMs that dynamically reweights adversarial examples through an f -divergence ambiguity set around the empirical training distribution. Our method optimizes the worst-case adversarial loss within a divergence ball around the empirical data distribution, automatically emphasizing harder adversarial examples. Using the convex dual formulation, the objective reduces to a log-sum-exp form under the KL divergence, with a dynamical parameter controlling the strength of reweighting. This study leads to a new class of information-theoretic objectives that significantly reduce attack success rates while maintaining model utility. Across multiple LLMs and attack settings, WARDEN substantially reduces attack success rates with computational and utility costs comparable to CAT-, CAPO-, and MixAT-based baselines, making it a practical approach for scalable robust alignment.

cs.LG↗

arXiv2025

Future-Proofing Authentication Against Insecure Bootstrapping for 5G Networks: Feasibility, Resiliency, and Accountability

The 5G protocol lacks a robust base station (BS) authentication mechanism during the initial bootstrapping phase, leaving it susceptible to fake BSs, spoofed broadcasts, and large-scale manipulation of System Information Blocks (SIBs). Existing solutions incur high communication overhead, rely on centralized trust, and lack accountability and long-term breach resiliency. Given the inevitability of BS compromise and the severe impact of forged SIBs as the root of trust (e.g., fake alerts, tracking, false roaming), distributed trust, verifiable forgery detection, and audit logging are essential yet remain largely unexplored. These challenges are further amplified by the emergence of quantum-capable adversaries. While NIST Post-Quantum Cryptography (PQC) standards are widely viewed as a path toward long-term security, their feasibility under 5G's strict packet-size, latency, and broadcast constraints has not been systematically studied. This work presents, to our knowledge, the first comprehensive network-level performance characterization of integrating NIST-PQC standards and conventional digital signatures into 5G BS authentication, showing that direct PQC adoption is impractical due to excessive signature sizes, fragmentation, and protocol-level delays. To address these challenges, we propose BORG, a future-proof authentication framework based on a Hierarchical Identity-Based Threshold Signature with Fail-Stop (HITFS) properties. BORG distributes trust across multiple BSs via threshold signing, enables post-mortem verifiable forgery detection, and provides tamper-evident, PQ-secure audit logging, while maintaining compact signatures that fit within a single SIB1 packet without fragmentation and incurring minimal UE overhead, as validated through our real over-the-air 5G testbed implementation.

cs.CR↗

arXiv2025

Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy

Federated learning (FL) enables organizations to collaboratively train models without sharing their datasets. Despite this advantage, recent studies show that both client updates and the global model can leak private information, limiting adoption in sensitive domains such as healthcare. Local differential privacy (LDP) offers strong protection by letting each participant privatize updates before transmission. However, existing LDP methods were designed for centralized training and introduce challenges in FL, including high resource demands that can cause client dropouts and the lack of reliable privacy guarantees under asynchronous participation. These issues undermine model generalizability, fairness, and compliance with regulations such as HIPAA and GDPR. To address them, we propose L-RDP, a DP method designed for LDP that ensures constant, lower memory usage to reduce dropouts and provides rigorous per-client privacy guarantees by accounting for intermittent participation.

cs.CR↗

arXiv2025

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce more accurate and grounded responses. While RAG has shown strong potential in reducing hallucinations and improving factual consistency, it also introduces new privacy and security challenges that differ from those faced by traditional LLMs. Existing research has demonstrated that LLMs can leak sensitive information through training data memorization or adversarial prompts, and RAG systems inherit many of these vulnerabilities. At the same time, reliance of RAG on an external knowledge base opens new attack surfaces, including the potential for leaking information about the presence or content of retrieved documents, or for injecting malicious content to manipulate model behavior. Despite these risks, there is currently no formal framework that defines the threat landscape for RAG systems. In this paper, we address a critical gap in the literature by proposing, to the best of our knowledge, the first formal threat model for retrieval-RAG systems. We introduce a structured taxonomy of adversary types based on their access to model components and data, and we formally define key threat vectors such as document-level membership inference and data poisoning, which pose serious privacy and integrity risks in real-world deployments. By establishing formal definitions and attack models, our work lays the foundation for a more rigorous and principled understanding of privacy and security in RAG systems.

cs.CR↗

arXiv2025

Standing Firm in 5G: A Single-Round, Dropout-Resilient Secure Aggregation for Federated Learning

Federated learning (FL) is well-suited to 5G networks, where many mobile devices generate sensitive edge data. Secure aggregation protocols enhance privacy in FL by ensuring that individual user updates reveal no information about the underlying client data. However, the dynamic and large-scale nature of 5G-marked by high mobility and frequent dropouts-poses significant challenges to the effective adoption of these protocols. Existing protocols often require multi-round communication or rely on fixed infrastructure, limiting their practicality. We propose a lightweight, single-round secure aggregation protocol designed for 5G environments. By leveraging base stations for assisted computation and incorporating precomputation, key-homomorphic pseudorandom functions, and t-out-of-k secret sharing, our protocol ensures efficiency, robustness, and privacy. Experiments show strong security guarantees and significant gains in communication and computation efficiency, making the approach well-suited for real-world 5G FL deployments.

cs.CR↗

arXiv2025

Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security

Federated learning (FL) enables collaborative model training while preserving user data privacy by keeping data local. Despite these advantages, FL remains vulnerable to privacy attacks on user updates and model parameters during training and deployment. Secure aggregation protocols have been proposed to protect user updates by encrypting them, but these methods often incur high computational costs and are not resistant to quantum computers. Additionally, differential privacy (DP) has been used to mitigate privacy leakages, but existing methods focus on secure aggregation or DP, neglecting their potential synergies. To address these gaps, we introduce Beskar, a novel framework that provides post-quantum secure aggregation, optimizes computational overhead for FL settings, and defines a comprehensive threat model that accounts for a wide spectrum of adversaries. We also integrate DP into different stages of FL training to enhance privacy protection in diverse scenarios. Our framework provides a detailed analysis of the trade-offs between security, performance, and model accuracy, representing the first thorough examination of secure aggregation protocols combined with various DP approaches for post-quantum secure FL. Beskar aims to address the pressing privacy and security issues FL while ensuring quantum-safety and robust performance.

cs.CR↗

arXiv2025

An Interactive Framework for Implementing Privacy-Preserving Federated Learning: Experiments on Large Language Models

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has greatly thwart the adoption of FL methods for training robust AI models in sensitive applications. Differential Privacy (DP) is considered the gold standard for safeguarding user data. However, DP guarantees are highly conservative, providing worst-case privacy guarantees. This can result in overestimating privacy needs, which may compromise the model's accuracy. Additionally, interpretations of these privacy guarantees have proven to be challenging in different contexts. This is further exacerbated when other factors, such as the number of training iterations, data distribution, and specific application requirements, can add further complexity to this problem. In this work, we proposed a framework that integrates a human entity as a privacy practitioner to determine an optimal trade-off between the model's privacy and utility. Our framework is the first to address the variable memory requirement of existing DP methods in FL settings, where resource-limited devices (e.g., cell phones) can participate. To support such settings, we adopt a recent DP method with fixed memory usage to ensure scalable private FL. We evaluated our proposed framework by fine-tuning a BERT-based LLM model using the GLUE dataset (a common approach in literature), leveraging the new accountant, and employing diverse data partitioning strategies to mimic real-world conditions. As a result, we achieved stable memory usage, with an average accuracy reduction of 1.33% for $\epsilon = 10$ and 1.9% for $\epsilon = 6$, when compared to the state-of-the-art DP accountant which does not support fixed memory usage.

cs.LG↗

arXiv2025

Securing 5G Bootstrapping: A Two-Layer IBS Authentication Protocol

The lack of authentication during the initial bootstrapping phase between cellular devices and base stations allows attackers to deploy fake base stations and send malicious messages to the devices. These attacks have been a long-existing problem in cellular networks, enabling adversaries to launch denial-of-service (DoS), information leakage, and location-tracking attacks. While some defense mechanisms are introduced in 5G, (e.g., encrypting user identifiers to mitigate IMSI catchers), the initial communication between devices and base stations remains unauthenticated, leaving a critical security gap. To address this, we propose E2IBS, a novel and efficient two-layer identity-based signature scheme designed for seamless integration with existing cellular protocols. We implement E2IBS on an open-source 5G stack and conduct a comprehensive performance evaluation against alternative solutions. Compared to the state-of-the-art Schnorr-HIBS, E2IBS reduces attack surfaces, enables fine-grained lawful interception, and achieves 2x speed in verification, making it a practical solution for securing 5G base station authentication.

cs.CR↗

arXiv2024

From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models

Recent privacy regulations (e.g., GDPR) grant data subjects the `Right to Be Forgotten' (RTBF) and mandate companies to fulfill data erasure requests from data subjects. However, companies encounter great challenges in complying with the RTBF regulations, particularly when asked to erase specific training data from their well-trained predictive models. While researchers have introduced machine unlearning methods aimed at fast data erasure, these approaches often overlook maintaining model performance (e.g., accuracy), which can lead to financial losses and non-compliance with RTBF obligations. This work develops a holistic machine learning-to-unlearning framework, called Ensemble-based iTerative Information Distillation (ETID), to achieve efficient data erasure while preserving the business value of predictive models. ETID incorporates a new ensemble learning method to build an accurate predictive model that can facilitate handling data erasure requests. ETID also introduces an innovative distillation-based unlearning method tailored to the constructed ensemble model to enable efficient and effective data erasure. Extensive experiments demonstrate that ETID outperforms various state-of-the-art methods and can deliver high-quality unlearned models with efficiency. We also highlight ETID's potential as a crucial tool for fostering a legitimate and thriving market for data and predictive services.

cs.LG↗

arXiv2024

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning

Federated learning enables the collaborative learning of a global model on diverse data, preserving data locality and eliminating the need to transfer user data to a central server. However, data privacy remains vulnerable, as attacks can target user training data by exploiting the updates sent by users during each learning iteration. Secure aggregation protocols are designed to mask/encrypt user updates and enable a central server to aggregate the masked information. MicroSecAgg (PoPETS 2024) proposes a single server secure aggregation protocol that aims to mitigate the high communication complexity of the existing approaches by enabling a one-time setup of the secret to be re-used in multiple training iterations. In this paper, we identify a security flaw in the MicroSecAgg that undermines its privacy guarantees. We detail the security flaw and our attack, demonstrating how an adversary can exploit predictable masking values to compromise user privacy. Our findings highlight the critical need for enhanced security measures in secure aggregation protocols, particularly the implementation of dynamic and unpredictable masking strategies. We propose potential countermeasures to mitigate these vulnerabilities and ensure robust privacy protection in the secure aggregation frameworks.

cs.CR↗

arXiv2024

Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement

Differentially private stochastic gradient descent (DP-SGD) has been instrumental in privately training deep learning models by providing a framework to control and track the privacy loss incurred during training. At the core of this computation lies a subsampling method that uses a privacy amplification lemma to enhance the privacy guarantees provided by the additive noise. Fixed size subsampling is appealing for its constant memory usage, unlike the variable sized minibatches in Poisson subsampling. It is also of interest in addressing class imbalance and federated learning. However, the current computable guarantees for fixed-size subsampling are not tight and do not consider both add/remove and replace-one adjacency relationships. We present a new and holistic R{\'e}nyi differential privacy (RDP) accountant for DP-SGD with fixed-size subsampling without replacement (FSwoR) and with replacement (FSwR). For FSwoR we consider both add/remove and replace-one adjacency. Our FSwoR results improves on the best current computable bound by a factor of $4$. We also show for the first time that the widely-used Poisson subsampling and FSwoR with replace-one adjacency have the same privacy to leading order in the sampling probability. Accordingly, our work suggests that FSwoR is often preferable to Poisson subsampling due to constant memory usage. Our FSwR accountant includes explicit non-asymptotic upper and lower bounds and, to the authors' knowledge, is the first such analysis of fixed-size RDP with replacement for DP-SGD. We analytically and empirically compare fixed size and Poisson subsampling, and show that DP-SGD gradients in a fixed-size subsampling regime exhibit lower variance in practice in addition to memory usage benefits.

cs.LG↗

arXiv2024

Unsupervised Threat Hunting using Continuous Bag-of-Terms-and-Time (CBoTT)

Threat hunting is sifting through system logs to detect malicious activities that might have bypassed existing security measures. It can be performed in several ways, one of which is based on detecting anomalies. We propose an unsupervised framework, called continuous bag-of-terms-and-time (CBoTT), and publish its application programming interface (API) to help researchers and cybersecurity analysts perform anomaly-based threat hunting among SIEM logs geared toward process auditing on endpoint devices. Analyses show that our framework consistently outperforms benchmark approaches. When logs are sorted by likelihood of being an anomaly (from most likely to least), our approach identifies anomalies at higher percentiles (between 1.82-6.46) while benchmark approaches identify the same anomalies at lower percentiles (between 3.25-80.92). This framework can be used by other researchers to conduct benchmark analyses and cybersecurity analysts to find anomalies in SIEM logs.

cs.CR↗

arXiv2023

Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning

Secure aggregation protocols ensure the privacy of users' data in federated learning by preventing the disclosure of local gradients. Many existing protocols impose significant communication and computational burdens on participants and may not efficiently handle the large update vectors typical of machine learning models. Correspondingly, we present e-SeaFL, an efficient verifiable secure aggregation protocol taking only one communication round during the aggregation phase. e-SeaFL allows the aggregation server to generate proof of honest aggregation to participants via authenticated homomorphic vector commitments. Our core idea is the use of assisting nodes to help the aggregation server, under similar trust assumptions existing works place upon the participating users. Our experiments show that the user enjoys an order of magnitude efficiency improvement over the state-of-the-art (IEEE S\&P 2023) for large gradient vectors with thousands of parameters. Our open-source implementation is available at https://github.com/vt-asaplab/e-SeaFL.

cs.CR↗

arXiv2022

Privately Fine-Tuning Large Language Models with Differential Privacy

Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models with billions and millions of parameters from scratch. Third parties, researchers, and practitioners are increasingly adopting these pre-trained models and fine-tuning them on their private data to accomplish their downstream AI tasks. However, it has been shown that an adversary can extract/reconstruct the exact training samples from these LLMs, which can lead to revealing personally identifiable information. The issue has raised deep concerns about the privacy of LLMs. Differential privacy (DP) provides a rigorous framework that allows adding noise in the process of training or fine-tuning LLMs such that extracting the training data becomes infeasible (i.e., with a cryptographically small success probability). While the theoretical privacy guarantees offered in most extant studies assume learning models from scratch through many training iterations in an asymptotic setting, this assumption does not hold in fine-tuning scenarios in which the number of training iterations is significantly smaller. To address the gap, we present \ewtune, a DP framework for fine-tuning LLMs based on Edgeworth accountant with finite-sample privacy guarantees. Our results across four well-established natural language understanding (NLU) tasks show that while \ewtune~adds privacy guarantees to LLM fine-tuning process, it directly contributes to decreasing the induced noise to up to 5.6\% and improves the state-of-the-art LLMs performance by up to 1.1\% across all NLU tasks. We have open-sourced our implementations for wide adoption and public testing purposes.

cs.CR↗

arXiv2022

FROG: Forward-Secure Post-Quantum Signature

Forward-secure signatures guarantee that the signatures generated before the compromise of private key remain secure, and therefore offer an enhanced compromise-resiliency for real-life applications such as digital forensics, audit logs, and financial systems. However, the vast majority of state-of-the-art forward-secure signatures rely on conventional intractability assumptions and therefore are not secure against quantum computers. Hash-based signatures (HBS) (e.g., XMSS) can offer forward-secure post-quantum security. However, they are efficient only for a pre-defined number of messages to be signed and incur high key generation overhead, highly expensive signing, and large signature sizes for an increasing number of messages. It is an open problem to develop quantum-safe forward-secure signatures that are efficient and practical with a signing capability scalable to their security parameters. In this work, we propose a new series of post-quantum signatures that we call FROG (Forward-secuRe pOst-quantum siGnature). Unlike HBS alternatives, FROG can achieve highly computational efficient signatures with sub-linear key/signature sizes and (practically) unbounded signing capability. This is achieved by transforming suitable post-quantum signatures into forward-secure settings via MMM constructions. We investigated the transformation of prominent post-quantum secure signatures such as Dilithium, WOTS, and BLISS with MMM. Our experiments indicate that FROG outperforms XMSS for the vast majority (if not all for a large number of messages) of performance metrics. We also discuss one-time variants of these base signature schemes that can push the performance of FROG to the edge. Overall, FROG shows a better performance than the existing alternatives with forward-security and therefore is an ideal alternative for the standardization efforts for forward-secure post-quantum signatures.

cs.CR↗

arXiv2021

Compatible Certificateless and Identity-Based Cryptosystems for Heterogeneous IoT

Certificates ensure the authenticity of users' public keys, however their overhead (e.g., certificate chains) might be too costly for some IoT systems like aerial drones. Certificate-free cryptosystems, like identity-based and certificateless systems, lift the burden of certificates and could be a suitable alternative for such IoTs. However, despite their merits, there is a research gap in achieving compatible identity-based and certificateless systems to allow users from different domains (identity-based or certificateless) to communicate seamlessly. Moreover, more efficient constructions can enable their adoption in resource-limited IoTs. In this work, we propose new identity-based and certificateless cryptosystems that provide such compatibility and efficiency. This feature is beneficial for heterogeneous IoT settings (e.g., commercial aerial drones), where different levels of trust/control is assumed on the trusted third party. Our schemes are more communication efficient than their public key based counterparts, as they do not need certificate processing. Our experimental analysis on both commodity and embedded IoT devices show that, only with the cost of having a larger system public key, our cryptosystems are more computation and communication efficient than their certificate-free counterparts. We prove the security of our schemes (in the random oracle model) and open-source our cryptographic framework for public testing/adoption.

cs.CR↗

arXiv2019

IoD-Crypt: A Lightweight Cryptographic Framework for Internet of Drones

Internet of Drones (IoD) is expected to play a central role in many civilian and military applications, that require sensitive and mission-critical information to be processed. It is therefore vital to ensure the security and privacy of IoD. However, unlike traditional networks, IoD has a broader attack surface and is highly energy-constrained, which hinder the direct adoption of standard cryptographic protocols for IoD. We propose an energy-efficient cryptographic framework (namely IoD-Crypt), which can potentially meet the requirements of battery-limited IoD. Specifically, IoD-Crypt utilizes special precomputation techniques and self-certified primitives to gain significant computation and communication efficiency over the standard public key cryptography (PKC) suites. Our integrations and optimizations are broadly applicable to key exchange, digital signature and public key encryption schemes that encompass generic applications of PKC in IoD. We prove that IoD-Crypt is secure in the random oracle model. We fully implemented IoD-Crypt on two common drone processors, namely 8-bit AVR and 32-bit ARM, and conducted an in-depth energy analysis. Our experiments (on both platforms) showed that IoD-Crypt offers up to 48x less energy consumption compared to standard techniques. We have open-sourced our implementations for wide adoption and public testing purposes.

cs.CR↗