arXiv subjects

Daniel Takabi

Publications and source records attributed to Daniel Takabi.

18 recordsLinked to original sources

arXiv2026

TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers

The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side threat we term TrustShift: a compromised MCP server behaves benignly during an initial conditioning phase, building operational reliance and suppressing agent skepticism, before switching to an adversarial payload once an interaction threshold is reached. The evasion is temporal, not syntactic: benign at deploy time, the server's defection is invisible to predeployment static analysis, which sees only the honest phase. Switched payloads range from overt structural violations to schema-valid manipulations, the latter preserving outer protocol compliance to evade runtime middleware filters. Crucially, TrustShift originates in the server-controlled tool channel, not user prompts (unlike indirect prompt injection) or the transport (unlike man-in-the-middle): the adversary is the trusted server endpoint itself. We introduce TrustShiftProbe, an evaluation and defense framework with four contributions: (1) a stateful temporal threat model of the agent-server lifecycle as a benign conditioning phase followed by an adversarial defection at a trust horizon; (2) a language-agnostic attack engine that instantiates each variant as a compromised MCP server across four production domains; (3) SHIELD, a multi-tier, zero-oracle runtime defense at the MCP transport boundary that audits server payloads against behavioral baselines learned during clean trust windows; and (4) a taxonomy of nine TrustShift variants spanning three execution mechanisms (structural violation, semantic corruption, scope expansion) and three adversarial objectives (disruption, exfiltration, and their combination). Across frontier proprietary and open-weight models, TrustShift attacks achieve a 69.5% mean attack success rate that SHIELD mitigates to 42.7%.

cs.CR↗

arXiv2026

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly rely on a fixed trigger shared by all poisoned inputs. This fixed-trigger design is a major weakness because many defenses detect or weaken the repeated patterns such triggers leave in data representations. Although input-aware dynamic backdoors have been studied in classical neural networks, transferring them to QNNs is difficult because quantum learning introduces new obstacles. In particular, measurement compresses the post-ansatz quantum state into a limited classical output, weakening supervision for a trigger generator, while individual density matrices fluctuate with the input and make per-sample contrastive learning unstable. To address these challenges, we propose Q-DIBA, the first input-aware dynamic backdoor attack for QNNs. Q-DIBA jointly trains a classical trigger generator and a victim QNN through a three-mode mini-batch strategy that supports clean behavior, attack activation, and trigger specificity. To provide stable quantum-level supervision, Q-DIBA introduces an ensemble density contrastive loss that operates on post-ansatz quantum states before measurement and contrasts mode-averaged density matrices rather than individual samples. Experiments on MNIST and Fashion-MNIST across multiple QNN architectures show that Q-DIBA achieves high clean accuracy, strong attack success, and high cross-trigger accuracy, demonstrating effectiveness, stealthiness, and input specificity. The attack also remains resilient against defenses including visual inspection, spectral-signature detection, and fine-tuning, suggesting that input-aware quantum backdoors are an important threat to secure QNN deployment.

quant-ph↗

arXiv2026

Laplace-Bridged Randomized Smoothing for Fast Certified Robustness

Randomized Smoothing (RS) offers formal $\ell_2$ guarantees for arbitrary base classifiers but faces two key practical bottlenecks: (i) it often relies on noise-augmented training to achieve nontrivial certificates, which increases training cost, can reduce clean accuracy, and weakens RS as a genuinely post-hoc defense; and (ii) certification is computationally expensive, typically requiring tens of thousands of noisy forward passes per input, which hinders deployment, especially on resource-constrained edge devices. To address both limitations, we propose Laplace-Bridged Smoothing (LBS), an analytic reformulation of RS that replaces high-dimensional input-space Monte Carlo (MC) sampling with efficient computations in a low-dimensional probability space. LBS preserves formal robustness guarantees without requiring noise-augmented training while substantially reducing certification burden. On CIFAR-10 and ImageNet, LBS attains stronger certified robustness than RS and reduces per-sample certification cost by nearly an order of magnitude. Notably, on NVIDIA Jetson Orin Nano and Raspberry Pi 4, LBS achieves speedups of up to $494\times$, enabling practical certified deployment on real-world edge devices. Finally, we provide theoretical justification for the analytic formulation and certificate validity of LBS.

cs.LG↗

arXiv2026

MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security

The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unlike prompt-only interactions, MCP exposes pre-execution artifacts, shared context, multi-turn workflows, and third-party supply chains to adversarial influence across independently operated components. While recent work has identified MCP-specific attacks and evaluated defenses, existing studies are largely attack-centric or benchmark-driven, providing limited guidance on where mitigation responsibility should reside within the MCP architecture. This is problematic given MCP's multi-party design and distributed trust boundaries. We present a defense-placement-oriented security analysis of MCP, introducing a layer-aligned taxonomy that organizes attacks by the architectural component responsible for enforcement. Threats are mapped across six MCP layers, and primary and secondary defense points are identified to support principled defense-in-depth reasoning under adversaries controlling tools, servers, or ecosystem components. A structured mapping of existing academic and industry defenses onto this framework reveals uneven and predominantly tool-centric protection, with persistent gaps at the host orchestration, transport, and supply-chain layers. These findings suggest that many MCP security weaknesses stem from architectural misalignment rather than isolated implementation flaws.

cs.CR↗

arXiv2026

BioShield: A Context-Aware Firewall for Securing Bio-LLMs

The rapid advancement of Large Language Models (LLMs) in biological research has significantly lowered the barrier to accessing complex bioinformatics knowledge, ex perimental design strategies, and analytical workflows. While these capabilities accelerate innovation, they also introduce serious dual-use risks, as Bio-LLMs can be exploited to generate harmful biological insights under the guise of legitimate research queries. Existing safeguards, such as static prompt filtering and policy-based restrictions, are insufficient when LLMs are embedded within dynamic biological workflows and application-layer systems. In this paper, we present BioShield, a context-aware application-level firewall designed to secure Bio LLMs against dual-use attacks. At the core of BioShield is a domain-specific prompt scanner that performs contextual risk analysis of incoming queries. The scanner leverages a harmful scoring mechanism tailored to biological dual-use threat cat egories to identify prompts that attempt to conceal malicious intent within seemingly benign research requests. Queries ex ceeding a predefined risk threshold are blocked before reaching the model, effectively preventing unsafe knowledge generation at the source. In addition to pre-generation protection, BioShield deploys a post-generation output verification module that inspects model responses for actionable or weaponizable biological content. If an unsafe response is detected, the system triggers controlled regeneration under strengthened safety constraints. By combining contextual prompt scanning with response-level validation, BioShield provides a layered defense framework specifically designed for bio-domain LLM deployments. Our framework advances cyberbiosecurity by formalizing dual-use threat detection in Bio-LLMs and proposing a structured mitigation strategy for secure, responsible AI driven biological research.

cs.CR↗

arXiv2026

DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated Learning

Personalized federated learning (PFL) creates client-specific models to handle data heterogeneity. Previously, PFL has been shown to be naturally resistant to backdoor attack propagation across clients. In this work, we reveal that PFL remains vulnerable to backdoor attacks through a novel frequency-domain approach. We propose DCInject, an adaptive frequency-domain backdoor attack for PFL, which removes portions of the zero-frequency (DC) component and replaces them with Gaussian-distributed samples in the frequency domain. Our attack achieves superior attack success rates while maintaining clean accuracy across four datasets (CIFAR-10/100, GTSRB, SVHN) compared to existing spatial-domain attacks, evaluated under parameter decoupling based personalization. DCInject achieves superior performance with ASRs of 96.83% (CIFAR-10), 99.38% (SVHN), and 100% (GTSRB) while maintaining clean accuracy. Under I-BAU defense, DCInject demonstrates strong persistence, retaining 90.30% ASR vs BadNet's 58.56% on VGG-16, exposing critical vulnerabilities in PFL security assumptions. Our code is available at https://github.com/NahomMA/DCINject-PFL

cs.CR↗

arXiv2025

NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks

Large Language Models (LLMs) have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn jailbreaks that distribute malicious intent across benign exchanges and bypass alignment mechanisms. Existing approaches often explore the adversarial space poorly, rely on hand-crafted heuristics, or lack systematic query refinement. We present NEXUS (Network Exploration for eXploiting Unsafe Sequences), a modular framework for constructing, refining, and executing optimized multi-turn attacks. NEXUS comprises: (1) ThoughtNet, which hierarchically expands a harmful intent into a structured semantic network of topics, entities, and query chains; (2) a feedback-driven Simulator that iteratively refines and prunes these chains through attacker-victim-judge LLM collaboration using harmfulness and semantic-similarity benchmarks; and (3) a Network Traverser that adaptively navigates the refined query space for real-time attacks. This pipeline uncovers stealthy, high-success adversarial paths across LLMs. On several closed-source and open-source LLMs, NEXUS increases attack success rate by 2.1% to 19.4% over prior methods. Code: https://github.com/inspire-lab/NEXUS

cs.CR↗

arXiv2025

HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement; and a Network Traverser for real-time adaptive attack execution. HarmNet systematically explores and refines the adversarial space to uncover stealthy, high-success attack paths. Experiments across closed-source and open-source LLMs show that HarmNet outperforms state-of-the-art methods, achieving higher attack success rates. For example, on Mistral-7B, HarmNet achieves a 99.4% attack success rate, 13.9% higher than the best baseline. Index terms: jailbreak attacks; large language models; adversarial framework; query refinement.

cs.CR↗

arXiv2025

Heterogeneous Graph Backdoor Attack

Heterogeneous Graph Neural Networks (HGNNs) excel in modeling complex, multi-typed relationships across diverse domains, yet their vulnerability to backdoor attacks remains unexplored. To address this gap, we conduct the first investigation into the susceptibility of HGNNs to existing graph backdoor attacks, revealing three critical issues: (1) high attack budget required for effective backdoor injection, (2) inefficient and unreliable backdoor activation, and (3) inaccurate attack effectiveness evaluation. To tackle these issues, we propose the Heterogeneous Graph Backdoor Attack (HGBA), the first backdoor attack specifically designed for HGNNs, introducing a novel relation-based trigger mechanism that establishes specific connections between a strategically selected trigger node and poisoned nodes via the backdoor metapath. HGBA achieves efficient and stealthy backdoor injection with minimal structural modifications and supports easy backdoor activation through two flexible strategies: Self-Node Attack and Indiscriminate Attack. Additionally, we improve the ASR measurement protocol, enabling a more accurate assessment of attack effectiveness. Extensive experiments demonstrate that HGBA far surpasses multiple state-of-the-art graph backdoor attacks in black-box settings, efficiently attacking HGNNs with low attack budgets. Ablation studies show that the strength of HBGA benefits from our trigger node selection method and backdoor metapath selection strategy. In addition, HGBA shows superior robustness against node feature perturbations and multiple types of existing graph backdoor defense mechanisms. Finally, extension experiments demonstrate that the relation-based trigger mechanism can effectively extend to tasks in homogeneous graph scenarios, thereby posing severe threats to broader security-critical domains.

cs.CR↗

arXiv2024

MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference

Due to the extensive application of machine learning (ML) in a wide range of fields and the necessity of data privacy, privacy-preserving machine learning (PPML) solutions have recently gained significant traction. One group of approaches relies on Homomorphic Encryption (HE), which enables us to perform ML tasks over encrypted data. However, even with state-of-the-art HE schemes, HE operations are still significantly slower compared to their plaintext counterparts and require a considerable amount of memory. Therefore, we propose MOFHEI, a framework that optimizes the model to make HE-based neural network inference, referred to as private inference (PI), fast and efficient. First, our proposed learning-based method automatically transforms a pre-trained ML model into its compatible version with HE operations, called the HE-friendly version. Then, our iterative block pruning method prunes the model's parameters in configurable block shapes in alignment with the data packing method. This allows us to drop a significant number of costly HE operations, thereby reducing the latency and memory consumption while maintaining the model's performance. We evaluate our framework through extensive experiments on different models using various datasets. Our method achieves up to 98% pruning ratio on LeNet, eliminating up to 93% of the required HE operations for performing PI, reducing latency and the required memory by factors of 9.63 and 4.04, respectively, with negligible accuracy loss.

cs.CR↗

arXiv2024

SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator

Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that produce high-quality AEs. Developing such models has been much slower in natural language processing (NLP) than in areas such as computer vision. This paper introduces a practical and efficient adversarial attack model called SSCAE for \textbf{S}emantic, \textbf{S}yntactic, and \textbf{C}ontext-aware natural language \textbf{AE}s generator. SSCAE identifies important words and uses a masked language model to generate an early set of substitutions. Next, two well-known language models are employed to evaluate the initial set in terms of semantic and syntactic characteristics. We introduce (1) a dynamic threshold to capture more efficient perturbations and (2) a local greedy search to generate high-quality AEs. As a black-box method, SSCAE generates humanly imperceptible and context-aware AEs that preserve semantic consistency and the source language's syntactical and grammatical requirements. The effectiveness and superiority of the proposed SSCAE model are illustrated with fifteen comparative experiments and extensive sensitivity analysis for parameter optimization. SSCAE outperforms the existing models in all experiments while maintaining a higher semantic consistency with a lower query number and a comparable perturbation rate.

cs.CL↗

arXiv2024

RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based representations often exhibit poor robustness in adversarial settings. In this paper, we introduce RobustSentEmbed, a self-supervised sentence embedding framework designed to improve both generalization and robustness in diverse text representation tasks and against a diverse set of adversarial attacks. Through the generation of high-risk adversarial perturbations and their utilization in a novel objective function, RobustSentEmbed adeptly learns high-quality and robust sentence embeddings. Our experiments confirm the superiority of RobustSentEmbed over state-of-the-art representations. Specifically, Our framework achieves a significant reduction in the success rate of various adversarial attacks, notably reducing the BERTAttack success rate by almost half (from 75.51\% to 38.81\%). The framework also yields improvements of 1.59\% and 0.23\% in semantic textual similarity tasks and various transfer tasks, respectively.

cs.CL↗

arXiv2024

I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption

In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned training data is limited. However, challenges surface when data sharing encounters obstacles due to stringent privacy regulations or user apprehension regarding personal information disclosure. Earlier works based on secure multiparty computation (SMC) and fully homomorphic encryption (FHE) for privacy-preserving machine learning (PPML) focused more on privacy-preserving inference than privacy-preserving training. In response, we introduce BlindTuner, a privacy-preserving fine-tuning system that enables transformer training exclusively on homomorphically encrypted data for image classification. Our extensive experimentation validates BlindTuner's effectiveness by demonstrating comparable accuracy to non-encrypted models. Notably, our findings highlight a substantial speed enhancement of 1.5x to 600x over previous work in this domain.

cs.LG↗

arXiv2024

MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption

Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services. However, the exchange of sensitive patient data, such as chest X-rays, poses inherent privacy risks when shared with third parties. Addressing this concern, we propose MedBlindTuner, a privacy-preserving framework leveraging fully homomorphic encryption (FHE) and a data-efficient image transformer (DEiT). MedBlindTuner enables the training of ML models exclusively on FHE-encrypted medical images. Our experimental evaluation demonstrates that MedBlindTuner achieves comparable accuracy to models trained on non-encrypted images, offering a secure solution for outsourcing ML computations while preserving patient data privacy. To the best of our knowledge, this is the first work that uses data-efficient image transformers and fully homomorphic encryption in this domain.

cs.CR↗

arXiv2023

An Insider Threat Mitigation Framework Using Attribute Based Access Control

Insider Threat is a significant and potentially dangerous security issue in corporate settings. It is difficult to mitigate because, unlike external threats, insiders have knowledge of an organization's access policies, access hierarchy, access protocols, and access scheduling. Several approaches to reducing insider threat have been proposed in the literature. However, the integration of access control and moving target defense (MTD) for deceiving insiders has not been adequately discussed. In this paper, we combine MTD, deception, and attribute-based access control to make it more difficult and expensive for an insider to gain unauthorized access. We introduce the concept of correlated attributes into ABAC and extend the ABAC model with MTD by generating mutated policy using the correlated attributes for insider threat mitigation. The evaluation results show that the proposed framework can effectively identify correlated attributes and produce adequate mutated policy without affecting the usability of the access control systems.

cs.CR↗

arXiv2022

SoK: Privacy Preserving Machine Learning using Functional Encryption: Opportunities and Challenges

With the advent of functional encryption, new possibilities for computation on encrypted data have arisen. Functional Encryption enables data owners to grant third-party access to perform specified computations without disclosing their inputs. It also provides computation results in plain, unlike Fully Homomorphic Encryption. The ubiquitousness of machine learning has led to the collection of massive private data in the cloud computing environment. This raises potential privacy issues and the need for more private and secure computing solutions. Numerous efforts have been made in privacy-preserving machine learning (PPML) to address security and privacy concerns. There are approaches based on fully homomorphic encryption (FHE), secure multiparty computation (SMC), and, more recently, functional encryption (FE). However, FE-based PPML is still in its infancy and has not yet gotten much attention compared to FHE-based PPML approaches. In this paper, we provide a systematization of PPML works based on FE summarizing state-of-the-art in the literature. We focus on Inner-product-FE and Quadratic-FE-based machine learning models for the PPML applications. We analyze the performance and usability of the available FE libraries and their applications to PPML. We also discuss potential directions for FE-based PPML approaches. To the best of our knowledge, this is the first work to systematize FE-based PPML approaches.

cs.CR↗

arXiv2022

SoK: Privacy-preserving Deep Learning with Homomorphic Encryption

Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data. With homomorphic encryption (HE) computation can be performed on encrypted data without revealing its content. In this systematization of knowledge, we take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We categorize the changes to neural network models and architectures to make them computable over HE and how these changes impact performance. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.

cs.CR↗

arXiv2019

Privacy preserving Neural Network Inference on Encrypted Data with GPUs

Machine Learning as a Service (MLaaS) has become a growing trend in recent years and several such services are currently offered. MLaaS is essentially a set of services that provides machine learning tools and capabilities as part of cloud computing services. In these settings, the cloud has pre-trained models that are deployed and large computing capacity whereas the clients can use these models to make predictions without having to worry about maintaining the models and the service. However, the main concern with MLaaS is the privacy of the client's data. Although there have been several proposed approaches in the literature to run machine learning models on encrypted data, the performance is still far from being satisfactory for practical use. In this paper, we aim to accelerate the performance of running machine learning on encrypted data using combination of Fully Homomorphic Encryption (FHE), Convolutional Neural Networks (CNNs) and Graphics Processing Units (GPUs). We use a number of optimization techniques, and efficient GPU-based implementation to achieve high performance. We evaluate a CNN whose architecture is similar to AlexNet to classify homomorphically encrypted samples from the Cars Overhead With Context (COWC) dataset. To the best of our knowledge, it is the first time such a complex network and large dataset is evaluated on encrypted data. Our approach achieved reasonable classification accuracy of 95% for the COWC dataset. In terms of performance, our results show that we could achieve several thousands times speed up when we implement GPU-accelerated FHE operations on encrypted floating point numbers.

cs.CR↗