278 papers
This paper proposes and validates an open-source RISC-V-based Trusted Execution Environment that acts as an external entropy service, enabling constrained IoT devices to securely obtain high-quality random numbers for cryptographic key generation by leveraging initial trust and potentially expanding with additional sensor-based entropy sources.
This paper introduces "Reasoning-Oriented Programming," an automated attack framework that bypasses Large Vision-Language Model safety alignments by chaining semantically orthogonal benign visual inputs to force the emergence of harmful logic only during late-stage reasoning, thereby outperforming existing jailbreak methods on state-of-the-art models.
ZipPIR is a high-throughput single-server Private Information Retrieval protocol that achieves over 2 GB/s performance without requiring client-side storage by compressing LWE ciphertexts into Paillier ciphertexts during an almost silent offline phase, thereby overcoming the scalability and dynamic database limitations of existing solutions.
This paper generalizes optimal partition selection algorithms to Rényi differential privacy, introducing an improved mechanism for bounded weighted partitions that enhances state-of-the-art methods while demonstrating a fundamental performance gap between additive and non-additive noise approaches when frequency data is also released.
This paper presents a new -differentially private algorithm for frequent substring mining that achieves near-optimal error guarantees while drastically reducing space and time complexity from to near-linear bounds through refined candidate generation and search space pruning.
This paper introduces AgenticCyOps, a security framework for enterprise multi-agent AI systems that mitigates emerging attack surfaces by formalizing tool orchestration and memory management as primary trust boundaries and applying five defensive principles aligned with global compliance standards to significantly reduce exploitable vulnerabilities in SOC workflows.
This paper presents a generalized framework for the SQIsign signature scheme by incorporating level structures into the isogeny challenge, which leads to a new explicit Deuring correspondence for supersingular elliptic curves and solutions to constrained norm equations.
This paper presents a novel hybrid framework that synergistically combines concolic execution, LLM-guided path prioritization, and deep learning to achieve provably sound and highly accurate detection of zero-day AI-generated malware, significantly outperforming conventional baselines on both standard and synthesized threat benchmarks.
This paper presents Lockbox, a Zero Trust architecture that ensures the secure processing of sensitive cloud workloads by enforcing strict isolation, least-privilege access, and end-to-end encryption, thereby enabling enterprises to safely leverage advanced capabilities like AI without compromising their security posture.
This paper introduces deZent, a decentralized implementation of z-anonymity that utilizes stochastic counting structures and secure sums to coordinate privacy-preserving data anonymization across sensor networks, achieving performance comparable to centralized approaches while significantly reducing communication overhead and minimizing trust in a central entity.
The paper proposes HeteroFedSyn, the first differentially private framework for synthesizing tabular data in horizontal federated settings, which achieves utility comparable to centralized methods by introducing noise-efficient dependency metrics, unbiased noise correction, and adaptive selection strategies to handle heterogeneous data distributions.
This paper introduces a physically consistent, IEEE-inspired benchmark dataset generator for evaluating passive reconnaissance in smart-grid communications, which models adversary-induced propagation effects across tiered network topologies to enable standardized, label-free assessment of graph-temporal and federated detection methods.
This paper introduces the Randomized Distributed Function Computation (RDFC) framework, a semantic communication approach that achieves local differential privacy and significantly reduces transmission rates compared to lossless methods, even in scenarios without shared randomness, by leveraging strong coordination metrics and randomized function generation.
This paper introduces CyberThreat-Eval, an expert-annotated benchmark derived from real-world Cyber Threat Intelligence workflows that addresses the limitations of existing evaluations by assessing Large Language Models across the full triage-to-reporting pipeline using analyst-centric metrics, revealing significant gaps in current models' ability to handle nuanced, actionable security insights.
The paper introduces JULI, a black-box jailbreaking technique that manipulates top-5 token log probabilities via a lightweight plug-in called BiasNet to effectively bypass safety alignment in API-accessible Large Language Models without requiring access to model weights or the generation process.
This survey systematically reviews decentralized federated learning methods from 2018 to early 2026, categorizing them into traditional distributed and blockchain-based architectures, proposing a unified challenge-driven taxonomy, and outlining future research directions to address security, privacy, and system-level trade-offs in coordinator-free settings.
This paper presents FlexServe, a high-performance and secure LLM serving system for mobile devices that leverages a novel Flexible Resource Isolation mechanism to overcome the significant overhead of ARM TrustZone, achieving up to 10.05× faster time-to-first-token and 24.30× faster multi-model workflow execution compared to baseline designs.
This paper introduces a comprehensive multi-vector privacy evaluation framework that quantifies memorization risks in Genomic Language Models by integrating perplexity-based detection, canary sequence extraction, and membership inference, revealing that these models exhibit measurable data leakage dependent on architecture and training dynamics.
This paper introduces MCP Bridge, a lightweight, LLM-agnostic RESTful proxy that enables Model Context Protocol servers to run in resource-constrained environments with enhanced security, while also presenting a fine-tuned Qwen3 model that achieves state-of-the-art performance on the MCPToolBench++ benchmark through advanced reinforcement learning techniques.
This paper introduces a differentially private, zero-order optimization framework that extends dataset condensation to non-differentiable clinical models, enabling the creation of compact, privacy-preserving synthetic datasets that facilitate the democratization of clinical data sharing without compromising model utility.