CyberSec Research

Internetware envisions autonomous software entities collaborating over the open Internet. Raft consensus is widely adopted for its simplicity and performance in distributed coordination, e.g., service registries and blockchains. However, Raft assumes crash faults only, making it vulnerable to Byzantine behaviors like election forgery and log tampering. Existing BFT protocols incur high overhead, while ad-hoc hardening lacks unified defense. We propose \textbf{TRM-Raft}, a Byzantine-resistant enhancement that non-intrusively integrates a Blockchain-based Trust and Reputation Model (B-TRM) into the consensus core. It quantifies multi-dimensional node behaviors, applies adaptive penalties distinguishing accidental faults from malice, and embeds reputation into leader election and log replication. A reputation-aware election penalizes term/index forgery, excluding low-reputation nodes from leadership. A Schnorr-signature-based mechanism lets followers verify log integrity; tampering triggers reputation decay and leader replacement. Evaluated on Hyperledger Fabric in a realistic Internetware setting, TRM-Raft keeps malicious leader ratio below 5\% even with 40\% Byzantine nodes, with <10\% throughput loss and <5\% latency increase over vanilla Raft. TRM-Raft offers a lightweight, practical trustworthiness path for Internetware systems relying on Raft.

Cryptoassets are increasingly entangled with the traditional financial system, and how this activity integrates into national economies and behaves under stress bears on financial stability and the design of public digital money. However, blockchain pseudonymity and the lack of geographic identifiers force existing work to rely on indirect proxies to infer and locate market participants. Here we use a regulatory registry that directly identifies the on-chain addresses of all crypto-asset service providers (CASPs) registered in Austria, reconstructing their on-chain transaction activity across Bitcoin, Ether, USDC, and USDT through May 2025, and separating retail-like from institutionally mediated flows. We find that Austrian CASPs intermediate roughly USD 30 billion with external counterparties and are integrated globally rather than domestically. In value, this activity is dominated by a few institutional counterparties; in number, by retail-like ones. Around three major shocks, the Terra-Luna collapse, the FTX bankruptcy, and the Silicon Valley Bank failure, the two groups respond through different mechanisms, and stablecoins do not act as a uniform safe haven. The clearest case is SVB, where retail-like deposits and institutional withdrawals are consistent with USDC's two-tiered redemption mechanism. These patterns are invisible in aggregate data. Registry-based, transaction-level measurement thus offers a reproducible, cross-jurisdictional basis for monitoring how cryptoasset markets transmit risk.

Proximity gaps are a property of error correcting codes that arise in the study of Interactive Oracle Proofs (IOPs) and Succinct Non-interactive Arguments of Zero Knowledge (SNARKs). Recent work of Goyal and Guruswami has established near-optimal proximity gaps for many families of codes, including subspace design codes, as well as random ensembles like random linear codes, Reed-Solomon codes with random evaluation points, and Gallager's ensemble of LDPC codes (Goyal & Guruswami, 2025). However, the parameters for these latter randomized ensembles are worse than the parameters for subspace design codes, and degrade as the degree ell increases. In this work, we obtain improved proximity gaps for random ensembles of codes, including random linear codes, Reed-Solomon codes with random evaluation points, and Gallager's ensemble. Quantitatively, our results for these random ensembles match the results that Goyal and Guruswami attained for subspace design codes. In fact, our techniques are a black-box transference from subspace design codes: any progress on subspace design codes will automatically lead to analogous progress for these random ensembles. To obtain our results, we extend the Local Coordinate-wise Linear (LCL) property framework developed by Levi, Mosheiff, and Shagrithaya and by Brakensiek, Chen, Dhar, and Zhang to a \textit{row-span constrained} version (Levi, Mosheiff & Shagrithaya, 2025; Brakensiek, Chen, Dhar & Zhang, 2025). This allows us to cast \textit{curve-decodability} -- a property that implies proximity gaps -- directly as a row-span constrained LCL property, and make use of that machinery. In contrast, because curve-decodability is not obviously a vanilla LCL property, prior work had worked with a proxy property instead, leading to the aforementioned parameter losses.

LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model. When provenance is disputed, attribution rests on the trajectory log (the record of tool calls, observations, and executed actions, not the model's reasoning), which the reseller stores and processes to meter usage. A watermark must therefore survive an adversary with full read/write access to the very evidence it is detected from; existing agent watermarks do not, as their attribution is read straight off that log. We present TRACE, to our knowledge the first agent watermark that is distortion-free in its action choices, self-synchronizing under deletion, and unconditionally invariant under rewriting. Deletion desynchronizes a position-derived key and rewriting alters content, so a deletion-robust key must come from content and a rewrite-robust key from position, and no single key serves both. A trajectory, however, has room for two watermarks. TRACE superposes a selection channel that sets which action is chosen, keyed on local content with a distortion-free sampler, so the agent's distribution is provably unchanged and detection resynchronizes after deletions, and a tally channel that sets how many records each decision group holds, keyed on the log's skeleton alone, which no rewriting can touch. We prove this behavioral watermark's signal is bought with decision entropy, each decision paying at least half its entropy and deterministic decisions nothing, and that erasing both channels forces the reseller to corrupt the trajectories it resells. On ToolBench and ALFWorld, TRACE matches the unwatermarked agent's success rate while its selection channel reaches detection scores near z = 100 on long-horizon trajectories, stays detectable under 70% step deletion, and keeps a tally channel exactly unchanged under LLM rewriting of any strength.

Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assistants, unsafe content in these agents can propagate through persistent state, reusable skills, and tool-mediated interactions, creating a substantially larger semantic attack surface. We observe that most security-critical interactions in such agents are transmitted through natural-language token flows, including memory updates, tool arguments, retrieved files, and inter-component communications. This observation enables a new security formulation: unsafe behavior can be intercepted as risky semantic flows before reaching privileged runtime sinks. Based on this insight, we propose TokenWall, a runtime defense framework that acts as a semantic firewall over agent token flows. TokenWall performs boundary-aware semantic auditing over these flows, constructing structured source-sink audit records, applying lightweight local inspection before execution, and selectively escalating ambiguous high-risk cases to stronger arbitration modules. Unlike prior approaches that rely on sparse auditing or remote large-model oversight, TokenWall enables full-coverage pre-execution mediation while reducing remote arbitration and latency. Experiments on CIK-Bench show that TokenWall reduces attack success rate to 12.5% while maintaining a 97.4% benign executable pass rate without human confirmation. TokenWall further introduces only 0.69 seconds of additional latency on benign cases, demonstrating that semantic runtime containment can achieve a practical security-utility trade-off for persistent AI agents.

QR codes are a ubiquitous part of daily life, widely trusted by millions. However, their lack of inherent security features has given rise to critical attack vectors, such as spoofing (quishing) on public infrastructure like self-service parking machines. To address this, we present a comprehensive evolution of secure QR code architectures. First, we evaluate a fully offline proof-of-concept leveraging EdDSA signatures (instantiated on the Ed25519 curve), CBOR-encoded certificates, and ZLIB compression, demonstrating that robust cryptographic integrity can be achieved within the QR code's strict static capacity. However, recognizing the scalability limitations of fully offline models-specifically the inability to perform immediate key revocation in massive smart-city IoT deployments-we subsequently propose a scalable Hybrid Web PKI architecture. This forward-looking model utilizes standardized JWKS endpoints, a Central Trust Registry, and URL fragments to ensure seamless backward compatibility with standard native cameras while providing dynamic, real-time validation for compliant applications. This dual-mode approach offers a practical, deployable path toward eliminating QR spoofing.

The NIS-2 Directive increases the need for continuous, auditable compliance evidence and motivates a shift from document-based compliance toward machine-readable compliance artifacts. The Open Security Controls Assessment Language (OSCAL) is a standard for this purpose, which the German Federal Office for Information Security (BSI) is adapting with Grundschutz++. However, companies are still managing extensive legacy IT security concepts (IT-SCs), and migrating them without verification could transfer outdated assets into the new format. While existing research primarily addresses the generation of new concepts, there is a lack of a verification framework that extracts legacy IT-SCs into an auditable intermediate representation, deterministically compares the extracted graph with an independently constructed reference state, and exports schema-valid OSCAL artifacts. This paper introduces the Automated Security Concept Structure Extraction and Reverse Topology-checking (ASSERT) Framework, which addresses this gap by using ontology-based extraction of legacy documents into formal document graphs, a five-class graph difference against a verified reference graph, and the export into schema-valid OSCAL outputs for system description and assessment evidence. Using the BSI's RecPlast dataset, we compare a local open-weight model and a commercial model across three configurations with different levels of reference-ontology exposure. The evaluation shows that ASSERT makes document-infrastructure inconsistencies measurable, but reveals a trade-off between discovering undocumented entities and enforcing a schema.

In critical infrastructure, operational technology environments often cannot be actively scanned, and yet active system feedback is needed for risk assessment and compliance. This paper presents a non-invasive, MCP-grounded multi-agent pipeline that converts natural-language system descriptions into source-verified knowledge graph and audit-ready artifacts in the NIST OSCAL format for continuous automated compliance management. The architecture decouples LLM-based reasoning from deterministic knowledge retrieval against authoritative threat-intelligence sources, reducing the risk of fabricated vulnerabilities and hallucinated attack paths. In an evidence-based synthetic scenario of a water utility, the pipeline achieves 0.90 CVE recall and perfect D3FEND recall. It generates a schema-valid OSCAL System Security Plan and an OSCAL Security Assessment Report. Nevertheless, the core insight is not that grounding via MCP eliminates errors (e.g., hallucinations) entirely from the pipeline, but that it shifts errors into the first phase of asset extraction from the natural language description. Here, a single incorrectly extracted entity can lead to genuine but irrelevant CVEs in subsequent stages of the pipeline, which consumes time and resources. However, it makes the remaining risk visible, verifiable, and suitable for a time-efficient manual review, since the infrastructure (e.g., version numbers, OS, etc.) is typically known.

While Large Language Models (LLMs) have become essential productivity tools, their integration into workflows without adequate safeguards creates significant risks. This paper proposes an open-source, privacy-focused, user-facing firewall designed to secure both web-based and programmatic LLM interactions. The architecture combines a browser extension and a proxy for total traffic interception across both HTTP(S) and WebSocket communications. At its core, a flexible multi-agent pipeline delivers data leakage prevention through a hybrid approach combining deterministic detectors with LLM-driven semantic analysis, proprietary code leakage prevention, and extensible components designed for future security enhancements such as prompt injection evasion. The framework's layered architecture enables deployment across heterogeneous environments, allowing organizations to balance computational cost, detection depth and latency. Evaluation results demonstrate it achieves F1 scores of up to 94.93% on optimal configurations.

Mini-programs have become a dominant paradigm for lightweight application deployment within super apps such as WeChat. To support seamless integration, super apps provide OAuth mechanisms for user login. However, improper integration of OAuth-based Authentication (OBA) flows by third-party developers can lead to critical security flaws. In this paper, we discover three new types of runtime OBA misuses that differ from prior static-code-based studies, enabling attackers to impersonate victims. To assess their real-world impact, we design and implement MINIAUTH, the first analysis framework for systematically analyzing OBA misuse at scale. MINIAUTH automatically pinpoints the OBA login page of a mini-program, executes the workflow dynamically, and analyzes its runtime behaviors. This enables it to handle obfuscated mini-programs and uncover vulnerabilities that existing approaches cannot detect. Applying MINIAUTH to 44,273 WeChat and 2,721 Baidu mini-programs, we uncover 1,834 misuse cases, including critical logic flaws that enable client-side identity forgery via exposed credentials and authentication bypass through static or plaintext identifiers. Our cross-platform evaluation further shows that such misuses are not confined to a single ecosystem but consistently appear across different mini-program platforms. We also identify a cryptographic design flaw in Baidu's OBA APIs that allows brute-forcing of session keys. We responsibly disclosed our findings to the developers and platforms, receiving acknowledgments and assigned CNVD/CNNVD IDs. These results underscore the need for more robust developer guidance and enhanced platform-level safeguards.

Smart homes have emerged as an important domain for HCI research, including work on usable security and privacy. Ideally, studies in these areas draw on datasets collected in real homes with real residents, capturing authentic device interactions, network traffic, and daily routines. However, creating such datasets is slow, expensive, and raises significant privacy concerns, as it requires long-term observation of people in their most private spaces. We propose using LLMs to generate diverse resident personas that interact with a simulated smart home, producing behaviorally grounded interaction schedules that can be executed on physical testbeds. We present (1) a design framework configuring simulated households across five socio-technical dimensions, (2) a multi-stage LLM pipeline that produces structured, executable device interaction schedules, and (3) a proof of concept demonstrating feasibility. As a work in progress, we aim to support scalable, privacy-conscious smart-home experimentation without relying on intrusive real-world data collection.

Digital-asset custody has been built on threshold multi-party approval: no operation proceeds unless $t$ of $n$ parties approve, and fewer than t compromised parties can neither authorize nor learn the authorization secret. Threshold signature schemes (TSS) have been the standard mechanism, but the post-quantum transition disrupts this model: standardized hash-based signatures resist efficient threshold signing, and lattice-based threshold protocols remain an emerging research track. We present a dual-gate architecture that separates member authentication from threshold authorization. Each member signs its approval with an ordinary signature under any EUF-CMA scheme; the quorum jointly produces a threshold seal from Shamir-shared secrets bound to the operation. The seal is the base instance of a programmable authorization computation: simple quorum is the minimal policy, while richer policies can evaluate secret-shared state without making the member-signature scheme part of that computation. The signature scheme is a deployment parameter: migrating from ECDSA to SLH-DSA or ML-DSA is a key rotation, not a protocol redesign, and members holding keys in commodity HSMs participate through the standard sign API. The architecture can be deployed wherever the asset-control path supports programmable verification, such as smart contracts, vault modules, or HSMs guarding a master key, and produces an enforcement-layer authorization rather than a native chain signature. Below-threshold secrecy is information-theoretic; an adversary holding $\geq t$ signing keys but no coefficient shares still cannot produce the seal.

In cloud computing, the public cloud service providers (CSPs) can provide cloud storage as the primary service while providing additional machine learning (ML)-based services by using the clients' data in storage. This business model extends the border of cloud computing services and brings in new business growth possibilities. Although it is promising, the model also brings in security concerns since the public commercial cloud cannot be fully trusted. For example, the public commercial clouds may sell clients' sensitive data to the government or other companies. To address the security concerns, an immediate solution is to require clients to encrypt their datasets before outsourcing to the cloud. However, if a database is formally encrypted, then the database contains only pseudorandom numbers, making it impossible to enable ML over it. In this project, we propose MLQENABLER (ML Queries Enabler) scheme to enable secure ML queries over encrypted database in cloud storage. MLQENABLER employs an index-aid approach to achieve security and ML capability simultaneously. Our initial experiments show that MLQENABLER achieves an acceptable security level while incurring only a slight ML performance degradation.

The rise of LLM-based agents with reasoning, summarization, and memory capabilities has created a new threat surface for online content that conventional defenses fail to address. Existing defenses like access controls can be circumvented by agents mimicking ordinary browsers, and injection-based defenses often degrade human readability. In this paper, we revisit the agent pipeline and identify context compression, which agents routinely invoke to fit context budgets, as a critical yet overlooked defense layer. We propose CAPE, a framework that protects high-value textual content by injecting invisible perturbations without changing its human-visible surface form, thereby inducing severe information loss during agent compression. CAPE extracts disruptive seed perturbations from an accessible surrogate compressor, then adapts them to query-only target compressors through prior-guided evolution and preference-calibrated candidate prioritization, achieving effective protection under a low query budget. Experiments on three content types and four compression settings show that CAPE improves information loss by up to 75.8% over the strongest baseline while keeping protected content visually indistinguishable from originals. CAPE also transfers to real-world settings, including the LangGraph agent workflow and GitHub Copilot, highlighting its generality and practical value. This paper aims to reveal context compression as a new defense layer, promoting content protection research in the agent era.

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning over page structure that is entangled with the attacker's content. We present Prismata, a defense enforcing contextual least privilege for web agents, constraining both what the agent sees and what it can do. Prismata's dynamic trust derivation produces permission labels for page content, with structural confinement guarantees, inspired by classical integrity models, that bound any labeling errors so that labels can only decrease in privilege and mislabelings are bounded. Prismata's mechanical confinement enforces these labels by redacting content and restricting agent capabilities. Importantly, these mechanisms require no developer annotations, so Prismata supports the long tail of websites. Across recent published web agent attacks, including adaptive variants, Prismata substantially reduces attack success while preserving benign task utility.

Federated reinforcement learning (FRL) is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhancing privacy and scalability in the decision-making process within dynamic vehicular environments. However, poisoning attacks pose a significant threat to the security and reliability of FRL-based systems, particularly in safety-critical autonomous driving, where this vulnerability remains largely unexplored. These attacks can compromise the global control model by subtly injecting malicious system parameters, leading to potential hazards. To counter these challenges, we present \alg (\underline{Sec}ure \underline{A}ggregation with \underline{p}oisoning-\underline{p}revention and historical reinforcement) as a defensive framework aimed at enhancing the robustness of FRL systems designed for safety-critical driving scenarios. \alg strategically integrates digital twins for rehearsal-based learning and leverages historical aggregated model parameters along with a selected central gradient to ensure that only benign data is aggregated, effectively mitigating the influence of malicious agents. Theoretical guarantees are provided for the convergence performance of \alg in the presence of poisoning attacks. We also validate the effectiveness of \alg using developed digital twins that model realistic highway environments to evaluate the control of autonomous vehicles under adversarial conditions.

Zero-knowledge machine learning (zkML) enables a server to perform verifiable inference while keeping model parameters private from the client. However, existing zkML systems incur prohibitive proof-generation costs. We observe that proof generation exhibits limited parallelism; that is, prover time does not decrease significantly as the number of threads increases. This limitation is because existing systems rely on monolithic proof computation, constructing a single proof for the entire machine learning model. We introduce zkComposer, a modular proof-construction framework that unlocks an additional dimension of parallelism, in addition to the parallelism in existing proof kernels. zkComposer decomposes the zkML proof of correct inference into independent sub-proofs, each covering a subset of the computation for inference e.g., each independent sub-proof can cover a subset of contiguous layers in the ML model. Adjacent sub-proofs are cryptographically linked through shared commitments to the activations from the boundary layer. zkComposer provides the same guarantees as the monolithic proof without requiring additional linking proofs or changes to the underlying cryptographic primitives. We implement zkComposer and evaluate it on three CNNs and GPT-2. We show that, on CNN workloads, zkComposer reduces prover time and response time by up to 3.25x relative to zkCNN [1]. On GPT-2, zkComposer reduces these times by up to 4.83x relative to zkGPT [2], when partitioning along the model layers. When partitioning across both model layers and input sequences in GPT-2, we show that zkComposer reduces prover time and response time by up to 6.84x relative to zkGPT [2].

Homomorphic encryption (HE) enables privacy-preserving inference under arithmetic constraints that restrict encrypted evaluation to additions and multiplications. As a result, non-polynomial activation functions must be replaced by polynomial approximations. Among polynomial approximation methods, minimax approximation, typically computed by the Remez algorithm, is a standard approach because it minimizes the maximum approximation error over a given design interval. For minimax polynomial design, the approximation interval is a critical hyperparameter: a wider interval improves robustness to large-magnitude inputs while increasing the minimax approximation error under a fixed degree budget. In this paper, we formulate this trade-off as a distribution-aware interval optimization problem, where the approximation interval is chosen to minimize the mean-squared error (MSE) with respect to the pre-activation distribution of interest. To effectively control outside-interval inputs, we combine minimax polynomials with domain extension functions (DEFs) and their HE-realizable polynomial counterparts, domain extension polynomials (DEPs), which approximate a clipping operation outside the design interval and thereby suppress uncontrolled polynomial extrapolation. We first derive an analytically tractable DEF-based proxy objective that captures the trade-off between within-interval minimax approximation error and outside-interval clipping error. We then connect this idealized objective to HE-realizable DEP constructions through an implementation-error decomposition with an accompanying upper bound.