Searcharxiv⌕ Search

subject

cs.CR

cs.CR: explore 594 source-linked works published from 2022 to 2026, with original documents and citations.

This collection is a preview while coverage and quality are evaluated.

Search within this collection

Coverage and selection

Includes records with this source-supplied label or an explicit phrase match in their metadata. Matches indicate a mention, not proof that a paper uses a method or tests a material. Source versions are consolidated by DOI.

Sources: arxiv. Collection updated 2026-09-16. Counts describe this index, not the complete source archives.

arXiv2026

Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack

Acoustic side-channel attacks (ASCA) on keyboards have gained increasing attention, yet impact of speech representation learning models in ASCA remains unexplored. Addressing this, we introduce KEYAC, a dataset designed to analyze representation generalization for ASCA under both standard and VoIP codec settings. On KEYAC, we evaluate six representation learning models under zero-shot and partial fine-tuning settings using fully connected and convolutional networks. Results show that while partial fine-tuning improves performance, models struggle to generalize across VoIP codecs. We hypothesize this limitation stems from inadequate modeling of nonlinear feature interactions in conventional fine-tuning architectures. To address this, we employ Kolmogorov-Arnold Networks (KAN) for fine-tuning. Empirical results show that KAN-based fine-tuning consistently outperforms the baselines and establishes a new state-of-the-art on KEYAC.

cs.CR↗
arXiv2026

Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?

Kubernetes is central to the cloud-native ecosystem, orchestrating containerised workloads. Recent work suggests that large language models (LLMs) can automate cluster security remediation, generating configuration patches from Kubernetes Security Posture Management (KSPM) findings without human authoring. Such systems, however, prompt the model with each finding in isolation from the live service call graph, assuming general hardening knowledge suffices. This assumption breaks down whenever a patch must preserve a runtime service dependency invisible to the model: an otherwise compliant fix then carries a destructive functional blast radius, crashing downstream callers or silently severing call edges across the cluster. Whether live cluster context improves patch correctness has not been measured under controlled conditions across multiple dependency classes. We introduce KuTIE (Kubernetes Topology Intelligence Engine), which builds a live cluster context from Istio call edges, Trivy KSPM findings, and the service-account bindings a workload reads, and conditions LLM patch generation on it. It is evaluated on VulnCare, a purpose-built 36-deployment, four-namespace healthcare cluster with 31 injectable findings across seven dependency classes, each labelled by topology dependence against cluster ground truth. Across 248 trials, topology context raises topology-dependent patch correctness from 11.1% to 78.0% ($Δ= 0.669$), a gap that holds for every model and for six of seven classes, from credential and network-policy ($Δ= 0.95$) to role-based access control ($Δ= 0.31$); a topology-independent control exhibits no such effect ($Δ= 0.0$), isolating the result from generic prompt enrichment. Supplying the live service-call graph and the service-account bindings it exposes thus improves remediation of topology-dependent findings well beyond scanner-only context.

cs.CR↗
arXiv2026

"I Thought You Were The Uncensored Place": Norms, Rules, and Moderation in AI-Generated Sexual Content Communities

As AI-generated sexual content (AIG-SC) is increasingly produced, online communities have emerged to support creators' needs. To understand whether and how community governance attempts work to prevent abuse while supporting free expression, we interviewed 24 members and moderators of large AIG-SC online communities (10,000+ members) with stated rules against creating and sharing abusive content (e.g., AI-generated CSAM). Through in-depth interviews, we offer insight into: (1) how and why these communities form; (2) implicit community norms; (3) explicitly stated rules---and their operationalization via content moderation; and (4) tensions between community values and moderation that leave space for abusive behavior. Our findings reveal a complex picture: while many creators and communities have personal boundaries against abuse, advice and resources for creating any form of AI-generated sexual content are accessible to users regardless of their intentions. Further complicating community moderation are norms that center anti-censorship and non-judgment, which leave moderators to justify their actions using the limits of the law and terms of service. We end by reflecting on the ways in which technical, community, and legal governance may most effectively mitigate the production of abusive content.

cs.CR↗
arXiv2026

0xPass: A Secure Protocol for Universal Cross-Chain Accounts

Universal accounts allow users to manage assets and execute operations across heterogeneous blockchain ecosystems through a single interface, but they introduce security and trust challenges involving authentication, authorization, transaction signing, key custody, recovery, and decentralization. This paper presents 0xPass, a modular protocol architecture for universal cross-chain accounts. 0xPass separates request orchestration, transaction solving, and transaction signing into interoperable layers. User-approved requests are bound to authenticated identities and authorized across layers, while threshold signatures prevent any single transaction node from holding a complete signing key. The design also supports constrained authorization delegation, transaction policies, account recovery, distributed key management, and auditable communication among independently operated sub-networks. We describe a staged deployment path from a centrally operated service to a permissioned network and ultimately to a permissionless network with third-party modules, collateral-backed onboarding, and rotating key-management committees. The resulting architecture provides a practical framework for extending cross-chain account functionality while progressively reducing centralized trust and preserving user control over transaction authorization.

cs.CR↗
arXiv2026

Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification

Post-deployment changes to large language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI governance when model weights are proprietary. We present a privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment. Our framework explores complementary probe families under different access models. Token-based probes operate in a black-box setting and require only the input interface, tokenizer, and vocabulary. Embedding-based probes require gray-box access to the embedding interface. Stress probes rely on additional interface capabilities but do not require full white-box access to model weights or architecture. This range allows probe selection to balance sensitivity, access requirements, and deployment cost. We evaluate probe constructions across LLM architectures, model-tampering scenarios representative of post-deployment attacks, and GPU platforms. Importantly, our experimental results demonstrate that token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting. Our Groth16 zk-SNARK workflow remains practical as the probe set scales from 1 to 50, where proving time increases from 1.02 to 1.78 seconds, verification remains near 0.84 seconds, and proof size remains constant.

cs.CR↗
arXiv2026

A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets

Deep learning-based side-channel analysis has historically focused on single-byte targets and manually cropped traces, which risks discarding exploitable leakage. While recent work has proposed specialized architectures and resampling techniques to address this gap, the literature lacks a simple transformer baseline for simultaneous full-key attacks on uncropped traces. We present an open-source transformer implementation for uncropped full-key attacks which uses the standard transformer encoder backbone, adapting only the input and output layers to the side-channel setting. We release our implementation, training recipes, and pretrained weights for uncropped ASCADv1f, ASCADv1r, and CHES-CTF-2018 which achieve performance competitive with previously-reported results, while using less than 10GB of VRAM and requiring at most 3.34 hours of training on a single NVIDIA A6000.

cs.CR↗
arXiv2026

Drishti: AI-Led Human-Directed Vulnerability Auditing for 5G Cores

Candidate generation for open-source vulnerabilities is no longer scarce. AI-assisted code review now produces defect candidates cheaply, and industry programs pair them with expert human triage. The remaining scarcity is validation and impact assessment, and the gap is largest in critical-infrastructure software like 5G cores. Here, validation has four costs: verification, reachability, impact, and fix-completeness. We present Drishti, an AI-led human-directed vulnerability audit framework with four components, one per cost: (i) an anti-pattern catalog for verification, (ii) critical-path triage for reachability, (iii) concentric validation for impact, and (iv) patch-review for fix-completeness. Across audits of Open5GS and free5GC, Drishti produced three findings. The first is a pre-authentication NULL-dereference in the Open5GS NRF multipart parser, fixed upstream with a CVE requested. The second is an ASN.1-PER memory amplification in the free5GC NGAP decoder. A 2-byte input from a rogue gNodeB OOM-kills the AMF in 6.2 seconds. The third is a defective patch on CVE-2025-69248 whose defense-in-depth check is dead code before authentication.

cs.CR↗
arXiv2026

Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization

Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence privacy-relevant memorization. We examine whether adding synthetic privacy-preference pairs to Direct Preference Optimization (DPO) is associated with lower canary-based memorization signals without modifying the objective or introducing a formal privacy mechanism. We propose Privacy-Pressure Preference Mixing (P3M), a data-composition protocol that varies the amount of privacy-preference data while keeping helpfulness and harmlessness preference data fixed. We evaluate a non-privacy Baseline and privacy-mixing ratios of 0.5, 1.0, and 2.0 using Gemma 3 270M-IT across five random seeds and validate the same four conditions using 4-bit-quantized Gemma 2 2B-IT across three seeds. Overall, under the tested conditions, privacy-preference mixing is associated with lower mean canary suffix log-likelihood proxy values across both model settings and lower aggregate membership-inference attack performance relative to the Baseline in the mixed-source 2B evaluation. Specifically, across the privacy-aware 2B configurations, the mean area under the receiver operating characteristic curve (AUROC) ranges from 0.596 to 0.629, and the mean area under the precision-recall curve (AUPRC) ranges from 0.541 to 0.575, compared with 0.804 and 0.790, respectively, for the Baseline. However, the reduction in membership distinguishability does not hold uniformly across data sources. Moreover, the relationship between the privacy ratio and harmlessness preference accuracy varies by model setting, whereas helpfulness preference accuracy remains broadly stable. These findings suggest that P3M should be viewed as a lightweight empirical protocol for examining privacy-utility-safety trade-offs rather than as a formal privacy guarantee or a defense against extraction attacks.

cs.CR↗
arXiv2026

Reducio: Optimized Confidential Serverless Cloud Deployments for Enterprise Customers

Serverless platforms based on Confidential Virtual Machines (CVMs) have been recently proposed to address the privacy problems with serverless functions, while achieving low latency. Unfortunately, our study indicates that to achieve these properties, existing proposals impose non-trivial requirements in terms of infrastructure changes and platform memory. Reducio is an alternate serverless platform design that does not require infrastructure changes and significantly reduces platform memory requirements. The platform is designed using two key components: (1) a function isolation framework inside a CVM based on kernel deprivileging features that minimize infrastructure requirements, and (2) a layer-wise caching methodology and algorithm that effectively uses a small in-memory function cache. Our evaluation indicates that Reducio can significantly reduce both platform requirements for deployment and function memory consumption.

cs.CR↗
arXiv2026

Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory

Long-term memory is becoming a core capability of LLM agents, enabling personalization and long-horizon interaction. However, memory mechanisms that retain, transform, or expose more information can affect both benign utility and susceptibility to memory poisoning. Existing evaluations typically measure memory utility or attack risk in isolation under fixed configurations, providing limited insight into how stage-specific design choices reshape their trade-off. We present \textsc{MemGauge}, a controllable framework that separately varies writing admission, management policy, and retrieval exposure under matched clean and poisoned conditions. Across 11 LLMs and two long-term memory benchmarks, controlled evaluations reveal three distinct profiles: a threshold-like risk transition during writing, policy-dependent local decoupling during management, and coupled growth of utility and risk during retrieval. We further apply analogous stage-level measurements to four existing memory systems and observe diagnostic associations qualitatively consistent with these profiles. These results show that targeted poisoning risk varies across memory operations and motivate stage-aware evaluation and control of LLM-agent memory.

cs.CR↗
arXiv2026

SIR: Self-improving Red-teaming for Compute Use Agents

Computer-use agents (CUAs) are agents powered by vision-language models (VLMs) that perceive a screen and operate an operating system through mouse, keyboard, and terminal interactions to automate everyday digital tasks. Their exposure to untrusted content creates a risk of indirect prompt injection (IPI), where an adversary embeds instructions in content the agent reads to redirect it toward actions that violate the user's intent. Evaluations based on fixed, hand-written injections may underestimate the risk posed by adaptive adversaries. We present SIR, a black-box self-improving IPI framework that (i) composes task-specific injections from a small library of reusable red-teaming principles stated in plain language and (ii) uses an iterative feedback loop to analyze unsuccessful attack trajectories and distill new, named principles that are retained in a shared library and reused across tasks. We target operating-system-level compromise and evaluate outcomes through deterministic checks on filesystem, service, and permission state rather than an LLM judge. An attack counts as successful only when both the adversarial objective and the benign user task are completed in the same execution. We evaluate three frontier CUAs, allowing SIR up to 10 attack attempts per case. It achieves joint attack success rates of 24% on Claude Opus 4.8 and 28% on Gemini 3.5 Flash, compared with 4% and 0%, respectively, for the benchmark's fixed, hand-written injection. The red-teaming principles discovered against one victim also improve attacks against other victims, including a different model family, without additional feedback.

cs.CR↗
arXiv2026

Extracting Knowledge from Tools in LLM Agents

LLM agents commonly use knowledge-based tools and access their underlying files, databases, and search indexes through tool invocation. This integration improves agents' ability to provide domain-specific services but also introduces the risk of tool-mediated knowledge extraction: source content exposed to an agent for legitimate responses may be progressively recovered from its outputs, enabling reconstruction of the knowledge source behind a target tool. This paper systematically investigates this risk and identifies two challenges introduced by tool invocation: tool-selection uncertainty, where an agent may invoke a competing tool instead of the target tool, and tool-argument compression, where fine-grained query information may be lost when the agent generates tool arguments. To tackle these challenges, we propose ToolSiphon, a query-only extraction attack that introduces two complementary signals: a target-discriminative signal, implemented through Tool Contrastive Analysis, to steer queries toward the target tool; and a response-grounded factual signal, implemented through Evidence Chained Feedback, to mitigate argument compression and progressively expand extraction coverage. Across three types of knowledge-based tools and six domain-specific datasets, ToolSiphon recovers 74.3% of source records on average when coarse-grained information about non-target tools is available, with 83.2% textual recovery and 90.2% semantic similarity. Even without such information, it recovers 66.3% of source records. ToolSiphon also remains effective against representative defenses and on three real-world agent platforms.

cs.CR↗
arXiv2026

Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers

Speech enhancement models are widely deployed as frontend modules in real-time speech services, yet their vulnerability to backdoor attacks remains unexplored. Existing backdoor methods are confined to classification tasks and rely on active trigger injection, an assumption incompatible with the passive processing nature of speech enhancement models. In this paper, we propose Ouroboros, a novel backdoor attack framework that leverages the ideal clean outputs of speech enhancement models as natural triggers, enabling inference-time activation without any external trigger injection. Extensive evaluations show Ouroboros achieves near-perfect attack success rates with minimal performance degradation on diverse models and datasets. Physical-world validations confirm that naturally recorded, unaltered clean audio can reliably activate the backdoor. Moreover, Ouroboros generalizes to targeted content-tampering attacks and remains effective against common filtering and finetuning defenses.

cs.SD↗
arXiv2026

A Roadmap to Available ICS Datasets and Testbeds for Cybersecurity Research

Industrial Control Systems (ICS) are the backbone of many critical infrastructure sectors; however, their growing level of connectivity, long lifespan and integration with the Information Technology (IT) environment introduces numerous cybersecurity challenges. The merging of Operational Technology (OT) and IT along with the deployment of Industry 4.0 technologies increases the attack surface of ICS environments, which in turn makes them more vulnerable to advanced cyber threats. Therefore, many researchers have shown interest in the field of cybersecurity of ICS. The topics of intrusion detection, anomaly detection, threat intelligence, attack simulation and resilience assessment of ICS have received much attention. Nevertheless, the development and testing of cybersecurity solutions for ICS remains to be challenging due to the lack of appropriate datasets and experimental environment. The main objective of this paper is to provide the roadmap of existing ICS cybersecurity datasets, testbeds and digital twins. This paper presents various taxonomies along with systematic analysis of architecture, characteristics, capabilities, pros and cons of these tools. The results of the analysis demonstrate the presence of persistent problems such as lack of standardized benchmarking datasets, lack of modern attack scenarios, insufficient number of datasets based on real operational traffic and difficulty in validating artificial intelligence-driven cybersecurity solutions. In addition to summarizing current research on ICS cybersecurity datasets and testbeds, this roadmap provides the identification of research gaps and recommendations on creation of new tools.

cs.CR↗
arXiv2026

KORD: Breaking the Key-Generation Bottleneck in Dealerless FSS via Protocol--Hardware Co-Design

Function secret sharing (FSS) has become a core primitive in privacy-preserving computation. However, each FSS invocation requires a fresh pair of function keys generated by a trusted dealer , expands the system's trust boundary and hinders practical deployment. Existing dealerless protocols eliminate this dependency, but incur substantial communication and a number of interaction rounds that grows linearly with the input bit-width, making key generation a major bottleneck. This paper present KORD, a protocol--hardware co-design that dramatically reduces the cost of dealerless FSS key generation. At its core is a pair of special-purpose chips that establish a common root of trust through mutual attestation and, within it, reconstruct FSS keys---eliminating the need for a dealer. This root of trust further forms a security boundary within which KORD restructures the generation protocol, collapsing the interaction of prior dealerless protocols into a single round, independent of GGM depth. A cross-key scheduling scheme then interleaves independent GGM-tree traversals, sustaining high computational throughput. KORD reduces per-key-generation communication by 7,633--70,274$\times$ over the state-of-the-art distributed FSS protocol across a comprehensive suite of FSS building blocks. Post-route analysis projects 12.75 million 32-bit DPF keys per second at 204 MHz using 21.5K LUTs, with 99.8% AES lane utilization. On private ResNet-18 inference, KORD cuts the share of end-to-end time spent on key generation from over 96% to 11.9%.

cs.CR↗
arXiv2026

Using Hyper-V Sockets for Real-time Data Extraction from a Malware Analysis Sandbox

We present how Hyper-V sockets can be used as a real-time communication channel for a malware analysis sandbox. We show that, compared to WinSock TCP sockets, Hyper-V sockets are not subject to TCP/IP-layer blocking and are not enumerated by common TCP connection listing tools. We compare the throughput of the two communication channels as a function of buffer size.

cs.CR↗
arXiv2026

Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems

Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which deployer released the reported bytes, and whether each cross-deployer edge was authorized. Credentials establish who may act, but need not bind them to later output bytes or prove both deployers authorized a dynamically created edge. We present a two-layer attestation design for dynamic delegation without a shared authority, public log, or precommitted workflow. A trusted deployer runtime signs a hash of each released output; this records released bytes but does not prevent prompt injection. Ancestry evidence records edge authorization. Under a unified threat model, we compare a signed linked list, a Merkle-chain variant, and a co-signed DAG. The primitives are standard; the contribution is deployer-side binding and the evidence needed for the two questions. After child-key compromise, the single-signer designs permit an unauthorized parent binding, whereas the co-signed DAG rejects it because the parent must authorize the edge. Fixed adversary matrices and regression tests validate the composed verifier. On an Apple M1 Pro, ancestry-only checks take 24.3-499.2us per hop. In a live local multi-service workflow, a parent discovers the child's A2A Agent Card; the child calls an MCP tool and releases local-LLM output: all 30 signed-DAG tasks passed complete verification, while a controlled child-key-only claim was rejected; its mean end-to-end latency was 813.1ms versus 770.8ms without evidence. In a complementary three-availability-zone AWS deployment, all 1,000 valid co-signed-DAG paths verified; issuance averaged 3.651ms and complete verification 5.015ms. The cloud result excludes TLS/mTLS, KMS, and model-serving latency.

cs.CR↗
arXiv2026

Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders

Backdoor attacks pose a serious threat to large language models (LLMs), but existing defenses remain fragmented, failing to pro?vide unified defense against both dirty-label and clean-label attacks. To investigate why such fragmentation arises, we present the first systematic feature-level mechanistic analysis of LLM backdoors using sparse autoencoders (SAEs). Starting from a 2 x 2 comparison of clean and poisoned models on clean and triggered inputs, we trace backdoor-induced logit shifts to high-contributing SAE features and categorize them into four roles: interac?tion, suppressed, mixed, and weight-modified features. This taxonomy reveals system?atic encoding differences: dirty-label back?doors are dominated by isolated interaction features, whereas clean-label backdoors rely more on heterogeneous mixtures of mixed and weight-modified features. These differ?ences explain why existing defenses remain fragmented across attack paradigms. We val?idate this hypothesis through inference-time feature clamping, which reduces ASR to at most 10.8% in most dirty-label settings and at most 15.4% in the majority of clean-label settings, while preserving benign-task perfor?mance. These results show that SAE-based analysis can explain defense fragmentation and guide interpretable backdoor mitigation.

cs.CR↗
Compare source metadata on this page
WorkPublishedSource identifierSource
Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack2026-09-212606.21210arxiv
Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?2026-08-312607.25995arxiv
"I Thought You Were The Uncensored Place": Norms, Rules, and Moderation in AI-Generated Sexual Content Communities2026-08-312608.13659arxiv
0xPass: A Secure Protocol for Universal Cross-Chain Accounts2026-08-312608.18359arxiv
Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification2026-08-312608.27954arxiv
A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets2026-08-312608.30105arxiv
Drishti: AI-Led Human-Directed Vulnerability Auditing for 5G Cores2026-08-312608.30112arxiv
Balancing Privacy, Utility, and Safety in LLM Alignment through Preference Optimization2026-08-312608.30141arxiv
Reducio: Optimized Confidential Serverless Cloud Deployments for Enterprise Customers2026-08-312608.30171arxiv
Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory2026-08-312608.30177arxiv
SIR: Self-improving Red-teaming for Compute Use Agents2026-10-032608.30207arxiv
Extracting Knowledge from Tools in LLM Agents2026-08-312608.30288arxiv
Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers2026-08-312608.30329arxiv
A Roadmap to Available ICS Datasets and Testbeds for Cybersecurity Research2026-08-312608.30332arxiv
KORD: Breaking the Key-Generation Bottleneck in Dealerless FSS via Protocol--Hardware Co-Design2026-08-312608.30379arxiv
Using Hyper-V Sockets for Real-time Data Extraction from a Malware Analysis Sandbox2026-08-312608.30383arxiv
Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems2026-08-312608.30387arxiv
Why Are LLM Backdoor Defenses Fragmented? A Feature-Level Explanation with Sparse Autoencoders2026-08-312608.30403arxiv

These are bibliographic comparisons, not experimental rankings. Follow the original document for methods and conditions.