Papers

Large language models are increasingly benchmarked against classical machine learning for network intrusion detection (NIDS), almost always using same-dataset evaluation, and that protocol turns out to be incomplete. Evaluating XGBoost and RoBERTa-LoRA on two independently collected NetFlow v2 networks across three axes (same-dataset performance, cross-dataset transfer, and adversarial evasion) reveals no universal winner. The two models are statistically tied same-dataset. XGBoost wins decisively under cross-dataset distribution shift, by 15 points of F1 and 25 points of balanced accuracy; on the target network RoBERTa-LoRA's false positive rate reaches 0.78, leaving it barely above chance despite a superficially moderate F1. RoBERTa-LoRA wins decisively under adversarial evasion, by roughly 17 points of F1 at a representative mid-range perturbation strength, while both models hold false positive rates below 0.01 throughout. The model an evaluator would recommend therefore depends entirely on which axis is tested, not on same-dataset accuracy alone. A staged feature-leakage ablation improves cross-dataset transfer non-monotonically, indicating the leakage signal is distributed across the feature representation rather than confined to a few columns, and cross-dataset transfer between our two networks is strongly directional. These results argue for evaluating NIDS models along multiple independent robustness axes, and with more than one metric per axis.

Private Evolution (PE) generates high-fidelity synthetic data in federated settings without exposing users' raw data. It aggregates clipped user votes over a shared candidate bank into a differentially private histogram, with noise calibrated to the worst-case user contribution. However, it is unclear whether an adversary can realize this worst-case privacy loss while following the PE protocol. We introduce a protocol-aware empirical audit in which the server commits to a single shared candidate bank and replaces roughly 1% of its entries with probes derived from a known, non-private canary. We evaluate eight attacks, including an unchanged-bank baseline, exact copies, plausible paraphrases, and high-entropy synthetic nonces. Experiments on Yelp and Sentiment140 show that natural-text attacks remain substantially below the theoretical DP bound, while nonce-based attacks yield considerably stronger bounds and come closest to the mechanism's privacy ceiling. These results quantify the gap between formal worst-case privacy and leakage achievable through protocol-valid candidate-bank manipulation.

To expand open-weight models' capacity without proportionally increasing computation, recent architectures incorporate gated parametric memory that retrieves learned values and injects them into intermediate representations. One representative design is Engram, which combines deterministic n-gram lookup with context-dependent gating over large learned memory tables. Despite these efficiency benefits, such modules create a distinct attack surface: their parameters can be modified independently of the backbone while directly shaping its computation. We introduce BadEngram, a post-training attack that exploits this surface to implant persistent, trigger-dependent behavior while leaving conventional backbone weights and the execution graph unchanged. We first establish the attack's feasibility and causally characterize its mechanism in a controlled Engram model, where BadEngram achieves 96.6% ASR on triggered inputs while limiting false activation on matched trigger-free inputs to 0.1% and preserving 99.6% clean accuracy. Replacing the retrieved memory values with their clean counterparts or closing the memory gates reduces ASR to at most 0.32%, confirming that the backdoor is expressed through the gated-memory pathway. We then test whether this vulnerability extends to production scale in Qwen3.8-Flash-Next's native Per-Layer Embedding subsystem. Using independently trained checkpoints for the two benchmarks, BadEngram achieves 47.8% ASR on HarmBench and 64.0% on AdvBench, while dormant-condition ASR remains 0.9% and 0.0%, respectively. These results identify native gated-memory parameters as a security-critical part of the model whose integrity cannot be inferred from an unchanged backbone.

Differential privacy provides a mathematical framework for guaranteeing privacy for sensitive data. In quantum information processing, the interaction of privacy constraints with quantum resources such as entanglement remains a question of interest. Given that the utility of many protocols, and often the presence of a quantum advantage, relies on quantum resources such as entanglement, it is crucial to understand when a privacy requirement for a quantum channel is compatible with the channel's ability to preserve entanglement. We study this question for quantum local differential privacy (QLDP). Our main result shows that every $\varepsilon$-QLDP channel with a $d$-dimensional input is entanglement-breaking whenever $\varepsilon\leq\log\frac{d}{d-1}$. We also prove an approximate version for $(\varepsilon,\delta)$-QLDP, where channels in the same high-privacy regime are close in diamond norm to an entanglement-breaking channel. We further prove a composition result for a collection of private quantum channels having entangled inputs and global measurements in the high-privacy regime. Finally, we apply our results to private quantum learning theory. We prove that any learning protocol using arbitrary quantum memory on copies of the output of an entanglement-breaking channel can be simulated by a protocol that measures the corresponding unprocessed input copies one at a time while storing only classical information. Combining this result with our high-privacy entanglement-breaking theorem, we show that under sufficiently private local noise, a learning protocol with quantum memory for purity testing and bipartite product testing is subject to the sample complexity lower bounds for protocols with single-copy measurements on the noiseless tasks. We also obtain stronger sample complexity lower bounds when a single highly private channel acts on the entire multipartite input.

Coordinated manipulation is collective: plausible accounts can jointly distort ratings, rankings, and engagement. Existing defenses primarily construct evidence from identities, graphs, content, or co-activity. We introduce an aggregate-first evidence layer that treats distortion of a context-level outcome distribution as the primary evidence object. The engine observes only a histogram, count, resolution, and reference distribution; identities are withheld until interval evidence is fixed. Because raw discrepancies have positive finite-sample expectation, we subtract a matched null expectation to obtain signed evidence and account for reference uncertainty. Participation logs then accumulate these fixed increments across accounts. We characterize matched-exposure divergence, bound self-influence, establish finite-horizon separation, and derive an exact linear reuse law for paired contexts. We evaluate the mechanism with controlled rotation experiments and paired counterfactual interventions on historical Amazon review streams. Historical reviews provide the behavioral background; synthetic identities provide known coalition membership, and exact clean twins provide counterfactual controls. In a fixed-attack sweep against historical non-donor comparison accounts, reassigning the same manipulated events across identities with increasing reuse raises account-score ROC-AUC from 0.500 to 0.797. With activity- and exposure-matched clean twins, frequency is at chance while counterfactual attribution achieves ROC-AUC 0.744. Under a mean-preserving shape intervention, Wasserstein-1 and Jensen-Shannon evidence achieve ROC-AUC 0.909 and 0.967, while frequency and mean-based attribution remain at chance. Aggregate evidence complements repeated co-activity, improving mixed-mechanism ROC-AUC from 0.750 to 0.874 with a simple untrained combination.

Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution feedback rather than through stable signatures or a single sandbox run. Existing static, dynamic, and benchmark-style evaluations rarely preserve public evidence that can be inspected, searched, and reused. We present SkillAtlas, a hosted attack trace library that converts private agent-skill security report bundles into reviewed, redacted, and searchable public cases. The library contains 3,014 cases, 6,589 traces, 151,131 steps, 233 affected skills, and 8 risk categories; 42.5% of successful cases first become successful after a non-success initial round, and trajectory-grounded labels improve pre-execution guard accuracy to 0.770.

Cross-chain bridges move value between blockchains. Intent-based bridges are a variant where a solver fulfills a user's declared outcome and an off-chain settlement layer later reconciles the fill against the deposit. Existing smart-contract fuzzers and static analyzers only flag known-bad code patterns or require protocol-specific hand-written assertions. This work formalizes a taxonomy separating invariant violations, safety properties a contract must enforce locally, from settlement exposures legitimately delegated to the off-chain settlement layer, and proposes IntentFuzz: a protocol-aware fuzzer that recovers a bridge's intent structure and deposit/fill function roles directly from unannotated Solidity source, then synthesizes multi-step fuzz sequences using an LLM-based fallback to help build call arguments. IntentFuzz recovers the correct intent structure in 9/9 benchmark protocols and classifies deposit and fill functions with 100% recall and 82% combined precision; across a corpus of 77 manually labeled contracts, it reaches 79.5% bridge-classification precision and 97.2% recall, and among confirmed bridges, struct selection reaches 88.6% precision and recall while deposit and fill classification each reach 100% recall. On 23 planted-bug mutants, IntentFuzz attains 100% recall and 100% precision, executing 273 templates (507 transactions in a median of 14ms per template). Across 24 real-world deployments, it confirms 17 genuine invariant violations under heuristic-only input generation, rising to 22 with its LLM-assisted tier enabled, spanning eight vulnerable GitHub repositories, each finding reproducible against public, deployed bytecode.

Hybrid fully homomorphic encryption~(FHE) inference improves the practicality of private inference by letting the server evaluate linear layers homomorphically while the client decrypts and applies nonlinearities. Recent schemes attempt to protect model confidentiality by returning noisy, output-permuted responses and appealing to shuffle-model differential privacy~(DP). We show that this protection fails in the correctness regime required by hybrid FHE systems. For a $d$-input linear layer, $d+1$ admissible queries suffice for exact recovery of a permutation-invariant layer summary, hence for perfect model distinguishability. We further show that input DP is orthogonal to model confidentiality and that the local-DP premise required for shuffle amplification cannot hold under correctness-bounded noise. We recover all linear layers of a \safhire{}-style ResNet-20 end-to-end from TFHE transcripts with zero error, using $d+1$ queries per layer for a total of $5{,}712$ direct queries. Under the same query model, we also confirm exact per-layer recovery on pretrained ImageNet-scale CNNs and ViT-B/16. The leaked spectra enable fingerprinting, lineage attribution, and improved logit-based extraction, while suppressing them destroys inference utility.

Semantic watermarking schemes such as Tree-Ring hide a detectable pattern in the initial noise latent of a diffusion model. Recent work shows these watermarks are not only removable but forgeable: an attacker who never sees the watermarking key can still produce images the genuine detector accepts. We reproduce the Reprompt forgery attack of Müller et al. against Tree-Ring on Stable Diffusion XL, using the authors' released code, on free-tier dual T4 GPUs with 14.6 GB of usable memory per device, substantially less per-GPU memory than the A40 hardware used in the original study. The attack reproduces. Over six trials of three arms we detect genuine images 6/6, clean images 0/6, and forged images 5/6, at 325-332 s per attack. Three further results came out of running it under constraint. The released detector computes a non-central $\chi^2$ statistic and hands back only its CDF, so we recovered the discarded statistic; our recovery matches the released detector exactly, and two natural scores built from it separate the forged arm from the clean null at AUC 0.861 and 0.972 on the same eighteen observations. Running SDXL in half precision requires patching the pipeline's direct autoencoder calls, and a controlled probe confirms the patched path leaves the detector statistic unchanged. Finally, we report a prediction we made from reading the detector source that our measurements then contradicted. The notebook, the pinned fork and every measurement artifact are released with the paper.

Mapping observed system behavior to standardized frameworks like MITRE ATT&CK is essential for threat-informed defense, but remains largely manual. Existing automated methods depend on Cyber Threat Intelligence reports, which offer only retrospective accounts of attacks. Low-level telemetry, i.e. kernel-level system calls, instead provides evidence of adversary behavior, yet its volume and complexity have limited its use for automated mapping. We present a methodology that collects kernel-level events via eBPF, correlates attacker commands into a provenance graph, and derives compact graph representations suitable for LLM-based reasoning. These representations are mapped to the MITRE ATT&CK framework using both pure LLM prompting and retrieval-augmented generation (RAG) grounded in the ATT&CK knowledge base, producing ranked technique candidates along with supporting rationales. We implement this methodology as an end-to-end pipeline, named Trace2ATT&CK and evaluate it on 347 Linux Atomic Red Team tests using locally deployed open-weights LLMs. RAG consistently improves ATT&CK mapping performance over pure prompting, while provenance graph substantially outperforms raw telemetry. These results show that local inference over graph-based behavioral descriptions can make automated ATT&CK mapping from kernel-level telemetry operationally viable, without compromising data confidentiality.

The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing an escalating risk as these models can bypass proprietary API guardrails when deployed locally. However, SLMs deployed as autonomous agents often struggle with long-horizon, exploratory tasks like cybersecurity Capture The Flag (CTF) challenges due to context bloat and cognitive degradation from accumulated tool-call outputs. To understand and mitigate this cybersecurity threat, we introduce context segmentation, a two-level agentic framework that divides complex exploitation tasks into manageable, contextually isolated sub-problems. Evaluating on the picoCTF dataset using memory-constrained gemma-4 models, we demonstrate that for the E4B model, our strategy acts as an intelligent search, achieving competitive rewards with superior token efficiency compared to brute-force retries, and successfully solving 18.52% of tasks that standard agentic execution fails to complete. Code is available at https://github.com/9xeb/context-segmentation.

Cyberwarfare has become a key component of contemporary geopolitical conflict. However, there has been extremely limited systematic investigation into how cybersecurity is handled by military organizations and personnel. The military context is unique compared to other operational ones, with immense resource availability (U.S. military spending approached 1 trillion dollars in 2024), a rigid chain of command, and extraordinary consequences for its actions. Thus, military cybersecurity is a distinct yet understudied topic. In this paper, we take an early step at understanding military cybersecurity by investigating how service members understand, recognize, and respond to cyber risk. We focus on maritime services and carefully consider organizational barriers to design an unclassified study and conduct semi-structured interviews with 20 military mariners from U.S. Navy and Coast Guard vessels. Through our investigation, we identify unique consequences of compromising military systems, including weapon takeover and purposeful geopolitical escalation. We find that cybersecurity is organizationally abstract on ships, so mariners build cyber risk models from informal experience rather than formal instruction. They nonetheless make cybersecurity actionable by recognizing operational impacts and responding with a safety-oriented incident-response model that creates resilience but may delay cyber attribution and containment. These findings inform actionable recommendations to help military operators frame cyber threats, merge longstanding nautical doctrine with modern systems, and apply military insights to the civilian sector, all to secure the broader maritime environment.

Can a finite verifier obtain public, model-relative evidence about response latency for sequential computation? Verifiable delay functions (VDFs) make this possible in principle: evaluation requires T sequential steps, whereas verification is efficient in the security parameter and polylogarithmic in the numerical value of T for standard constructions. Thus a delay can be astronomically large to evaluate yet succinctly represented and feasibly checked. A VDF proof for a chosen message alone is insufficient because it may be precomputed. We specify and analyze Fresh-Challenge VDF Attestations (FCLA), a protocol composition that binds a VDF to an unpredictable public challenge, a message, and independently auditable release and receipt records. Under explicit assumptions about VDF sequentiality, the challenge source, witness logs, and a calibrated upper bound on an adversary's sequential evaluation rate, an accepted FCLA transcript is inconsistent with post-challenge generation by an adversary in that bounded model. The result neither identifies a named claimant nor excludes relaying, outsourcing, or a faster unmodeled machine. A benchmark of the public reference implementation confirms the expected empirical separation between evaluation and verification on one documented machine. Our contribution is a protocol/design analysis and benchmarked reference implementation layer, not a new VDF construction or cryptographic primitive.

The actions of frontline law enforcement officers in the initial hour of a cyber incident play a vital role in determining the ultimate success of an investigation. The minor mistakes they commit might result in irreversible critical impacts. The integrity of the investigation can be compromised, and the prosecution of cyber criminals can be hindered due to minor mistakes that happen in the initial hour. These are mainly because of the volatile nature of digital artifacts that might lead to procedural errors and evidence attrition. This paper provides a systematic survey of decision-support architectures designed to assist first responders of a cybercrime, categorizing them into playbooks, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) frameworks, and Agentic AI systems. The survey critically considers the constraints of limited technical proficiency and inconsistent forensic infrastructure in a practical scenario. Our analysis identifies RAG-based systems as a relatively viable intermediate solution due to their natural language adaptability. However, significant risk factors like prompt sensitivity and the potential for confident hallucinations in legal contexts pose a major challenge. Furthermore, we review current benchmarks in cybersecurity and demonstrate that they are not sufficient to capture the specific safety and legal requirements of law enforcement, focusing on the initial hour of the cybercrime. We conclude by arguing for the necessity of a new evaluation benchmark focused on naive query robustness and evidence preservation, so as to ensure that AI-driven guidance aligns with the mandatory demands of judicial proceedings.

As the threat landscape against industrial control systems is dynamic, effective security requires detection strategies capable of timely reactions to these evolving threat situations. To address this problem, we propose the idea of a counter-threat intelligence sharing based mechanism to select appropriate detectors for current circumstances. To highlight the potential of this mechanism, we conduct attack-level performance evaluations of various intrusion detection systems. Results show the variance of intrusion detection performance depending on the attack scenario, emphasizing the benefits of such a mechanism for industrial control system security

With transciphering, a server converts symmetrically encrypted records into homomorphic ciphertexts without learning the records or the symmetric key. For the PASTA cipher, this conversion involves dense linear maps whose implementation depends on how record words are arranged in the ciphertext. We ask whether rearranging a fixed batch can reduce its conversion cost. Instead of storing each record's words in a contiguous block, our layout interleaves records so that cyclic word shifts preserve each record's positions, which form a coset of a cyclic subgroup. For direct evaluation as a sum of masked translations, we characterize the required displacements and relate their counts, 255 for the contiguous layout and 128 for the subgroup layout, to a prior transversal-difference invariant. We implement three equally batched schedules for complete PASTA-3 conversion and subsequent public subset-sum queries in HElib. Across twelve paired corpora under six homomorphic keys, all 24 direct and subgroup conversions and all 48 subsequent queries return the expected values and required zeroes. The median paired ratio of direct to subgroup server cost is 1.60, including fresh public generation, conversion and two queries. The reduction comes with less remaining noise capacity. These results establish a packing-dependent cost–noise tradeoff.

Distributed Denial-of-Service (DDoS) attacks remain a serious threat to transport networks, with recent attack volumes exceeding 30 Tbps, and the telecommunications industry being the main target. Recent work has yet to study the impact of the hosting software architecture on network monitoring solutions, or to assess recent algorithms for improving attack detection. This paper presents a Network Intrusion Detection System (NIDS) for DDoS detection in transport networks, developed in collaboration with Ericsson. Building on a statistical baseline, we improve detection effectiveness with an Isolation Forest trained on a wider set of flow features, extracted by GoFlowMeter, our open-source Go implementation of CICFlowMeter, and we integrate eBPF/XDP so that the NIDS filters real traffic at the kernel level. We further compare three deployments, monolithic, Kafka-based, and gRPC-based microservices, on a Raspberry Pi 5 testbed replaying the CIC-DDoS2019 dataset as real network traffic. Detection quality is governed mainly by the choice of detector rather than by the transport: the Isolation Forest raises recall and F1 score (0.965 live in the monolithic variant) over the baseline by flagging low-volume attack windows that the baseline misses. The transport is not neutral, however: gRPC reaches almost the same accuracy as the monolithic variant while adding less than 2 milliseconds of transport time per window, whereas the asynchronous Kafka pipeline trails by roughly nine percentage points and adds about 27 milliseconds. These findings clarify the trade-off between detection quality and architectural overhead when deploying a NIDS on resource-constrained hardware.

When an autonomous AI agent does something consequential, what can be proven about what it did? Agent-observability platforms capture traces, but a trace is mutable: alterable undetected, with no recipe for re-executing it, silent on whether captured secrets were removed. Regulation (EU AI Act, ISO 42001, NIST AI RMF) presumes records an independent party can check. We present NovaFabric, producing audit-grade execution evidence: provider-neutral, tamper-evident, replayable, shareable. It records an agent run, without modifying agent logic, into a portable Run Capsule (fifteen-entity schema), sealed with a holistic DSSE signature, RFC 3161 timestamp, Merkle log and redaction attestation. Sealed runs are re-executable under a four-mode replay protocol and exportable as an Evidence Bundle for third-party verification with stock tooling (specified, not evaluated). The contribution is integration, not new cryptography: OpenTelemetry, DSSE/in-toto and W3C PROV. We evaluate eight research questions at measured scope. Mocked replay serves every model response from the capsule (no live model call, 10/10) but is offline w.r.t. models, not the network; only 2/10 tool-using workloads completed; the gap is missing tool-response substitution. Tampering is rejected across three tested classes. Declared-stream completeness is 0.652 (95% CI +/-0.064, ten scenarios). A repaired rule pack redacts 14/14 credential types, preserving 9/9 decoys; diff localises 140/140 mutations. Blast-radius queries: 45.5ms p99 over 10M edges (3.3x faster than a columnar baseline), 167.9ms over 100M (1 client, n=30). A 314-machine, ten-region run finds capsule REST ingest lossless but capped at 61.6 req/s (p99 26.8s) by per-worker serialisation. Six defects found in NovaFabric and its evaluation corpus: four fixed, one withdrawn, one open. Verification is conditional on a stated trusted computing base.

Arm TrustZone for Armv8-M isolates Secure and Non-secure software, but developers must still coordinate peripheral attribution, interrupt routing, initialization, and gateway interfaces across separately built firmware images. Inconsistent assumptions between these images can compile successfully and emerge only as faults on the target device. We present MicroHasTEE, a multiparty programming framework that expresses both firmware applications as participants in one typed Haskell program. MicroHasTEE represents peripheral authority with type-level capability ledgers and uses indexed setup computations to track resource acquisition, configuration, transfer, and finalization. Domain-specific effect types restrict peripheral operations and interrupt callbacks to the participant that holds the corresponding authority, while typed callable handles describe the Secure services available to Non-secure code. MicroHs compiles the shared program twice to produce separate bare-metal Secure and Non-secure firmware images. We implement MicroHasTEE for an STM32U5 Nucleo board, including TrustZone configuration, peripheral drivers, and a serialized gateway for cross-domain Haskell calls. For programs expressed through its interface, MicroHasTEE rejects inconsistent resource use, attribution changes after configuration, callbacks in the wrong domain, and calls to unregistered Secure services. A door-lock case study demonstrates feasibility, with firmware images occupying 232.7 KiB and 228.4 KiB of flash and approximately 220 KiB of SRAM per domain.

Privacy impact assessment (PIA) is a critical instrument for institutions to proactively identify privacy risks and develop mitigation strategies before system deployment. While mandated across regulatory and institutional contexts, executing PIA requires extensive privacy and technical expertise, posing a particular challenge for teams without access to such resources. Prior work shows the potential of leveraging large language models (LLMs) to assist practitioners' privacy decisions, but little is known about how accurately and reliably LLMs can automate PIA. To this end, we develop PIA-Bench, the first open benchmark for evaluating LLMs on real-world PIAs. We first audited 499 expert-authored PIAs published by US federal agencies and curated 73 structured PIAs, comprising a total of 451 privacy risk and 831 mitigation items, to evaluate LLMs' ability to assess privacy risks and propose mitigations of complex systems. Our results show that off-the-shelf LLMs produce meaningful assessments and identify avenues for future improvement. Finally, we call for improving domain-specific workflows for LLM agents, developing accountable LLM infrastructure, and designing new quality standards for PIAs.

Metaverse platforms increasingly derive their success from user-generated virtual worlds: self-contained social and interactive environments, which can be created by any ordinary user and scale to billions of visits. Platforms such as Roblox, Horizon Worlds, and VRChat now host millions of creator-built worlds that govern how users see, hear, and interact with one another. While this model enables rapid growth and creativity, it fundamentally delegates control over social interactions and world behavior to untrusted users. In this paper, we present the first systematic security and privacy assessment of metaverse world creators. We survey 25 platforms that support user-created worlds and analyze their world-creation capabilities. Guided by this analysis, we design and implement five novel attacks that exploit creator-provided tools to violate spatial, visual, and auditory constraints in immersive environments, enabling covert user surveillance and manipulation without software vulnerabilities or developer-level privileges. We further show that five previously-proposed attacks can be replicated using only standard world-creation features. Finally, we find that existing platform vetting, runtime protections, and creator policies are insufficient to mitigate malicious world-creator behavior, revealing a fundamental mismatch between users' privacy expectations and the powers granted to world creators.

We study combinatorial optimization problems under the constraint of $\epsilon$-differential privacy ($\epsilon$-DP). Given the strong lower bounds for explicitly outputting solutions, we work within the implicit representation framework of Gupta et al. (SODA 2010), where a private polynomial-time randomized "encoder" generates a representation of a solution, and a "decoder" uses this representation along with the input to extract a valid final solution. In this work, we generalize this framework by allowing the encoder to run in fixed-parameter tractable time. This circumvents approximation barriers inherent to polynomial-time algorithms and obtains improved guarantees for many fundamental combinatorial optimization problems. Finally, we establish the first representation-independent lower bounds for our framework. Assuming a non-uniform variant of the Gap Exponential Time Hypothesis, for sufficiently small $\epsilon > 0$, we prove that no $\epsilon$-DP encoder-decoder pair can achieve certain approximation guarantees, if the decoder runs in subexponential time. We further provide representation-dependent lower bounds that hold even for larger $\epsilon$.

Commercial security gateways repeatedly ship implementation bugs in the code path between the network and the policy decision: hand-written enforcement logic that diverges from the policy author's intent, and ad-hoc request parsers at the network boundary that introduce memory-safety flaws of their own. In both cases the bug is in the deployed enforcement code, not in the policy. Existing approaches either leave the enforcement runtime unverified or connect a formal model to a hand-written engine only by differential testing. Our contribution is a class result: a forward-only, backtrack-free EverParse validator is a verified recognizer for a bounded, finite-state class, and access-control decision functions with fixed-offset fields and bounded disjunction belong to it, so one machine-checked proof transfers to every policy in the class rather than being re-established per policy. Concretely, we encode a bounded policy language's decision function into a fixed-size byte buffer and verify the enforcement code once—covering all byte values—with an SMT solver, proving the validator accepts if and only if the decision function accepts, for every policy, request, and session. Editing rule content over a fixed endpoint set then needs no new proof; adding endpoints reruns the toolchain; extending the language needs new proofs. We establish faithful enforcement of a policy, not that a policy is itself secure. The verified gate is platform-independent, requiring only EverParse/Z3 and a C compiler, whose correctness we assume. We demonstrate a deployment on the seL4 microkernel, which ensures every request passes through the gate and that unverified components cannot corrupt the verified enforcement chain.

The security and liveness of Proof-of-Work (PoW) blockchains fundamentally depend on the economic rationality of miners. Existing incentive-driven denial-of-service attacks, such as BDoS, can deter rational miners from participating, but require the attacker to continuously absorb substantial economic losses and are therefore difficult to sustain in high-value networks. Meanwhile, prior infiltration-based withholding attacks are designed to extract revenue rather than to directly disrupt chain liveness. We present PDoS, a hybrid attack that combines block header signal deterrence with parasitic revenue extraction. PDoS disrupts blockchain liveness while exploiting the victim pool's share-reward mechanism to subsidize the attack cost, thereby lowering the adversarial hash-power threshold required to induce rational miners to shut down. We further show a counterintuitive result: in high-fee or high-MEV environments, higher block value can make PoW systems less secure by increasing the attacker's parasitic revenue and pushing the attack across the break-even point into a self-sustaining, or even profitable, regime. To the best of our knowledge, PDoS is the first attack to demonstrate that disrupting PoW blockchain liveness can be economically self-sustaining and even profitable.

Sensitive attributes such as age, income, and occupation can be inferred from user-generated content by aggregating indirect cues across many ordinary posts. LLM-based profilers can perform this aggregation automatically and with high accuracy, which makes large-scale personal attribute inference a major privacy threat. Existing LLM-based profilers, however, offer limited insight into which specific posts, concepts, and relationships made an inference possible, which is key to targeted privacy mitigation, i.e., redacting or rewriting only the few posts that actually leak an attribute, rather than perturbing entire histories. We introduce GraphProfiler, an auditable LLM-based profiler that represents each user's post history as a source-linked personal knowledge graph where nodes and edges trace back to the originating post and resolves attribute predictions to cited graph records and source texts. GraphProfiler reaches 86.7% attack success rate on the eight-attribute SynthPAI benchmark, within two points of strong text-only baselines, and 84.6% on PANDORA, while citing supporting evidence for over 98% of predictions. Our controlled ablation experiments provide evidence that the cited posts contribute to attack success, as removing them reduces the attack success rate substantially more than removing an equal number of random posts.

Insecure Direct Object Reference (IDOR), often modeled as Broken Object-Level Authorization (BOLA), remains prevalent in Java database applications because identity and authorization checks at the controller or service layer are disconnected from SQL execution based on resource identifiers. Existing work largely detects these vulnerabilities but offers limited low-intrusion runtime protection for legacy Java-SQL applications. We present IDORacle, a template-guided SQL-sink interception and rewriting framework for preventing horizontal privilege escalation at runtime. IDORacle propagates authenticated identity context across HTTP requests, asynchronous tasks, and data-access boundaries through a server-side trace identifier. At the MyBatis/JDBC boundary, it extracts SQL templates, computes dual fingerprints, and performs one-time template analysis to generate reusable mediation plans. During execution, it combines subject context, SQL ASTs, table metadata, and cached authorization proofs to permit, rewrite, or block operations. Its guard model supports direct ownership predicates, join-derived ownership, probes for group-owned resources, role-sensitive state transitions, and sensitive-column mediation. A Java-SQL benchmark grounded in real-world CVE reports shows that IDORacle prevents the tested horizontal authorization violations with a worst-case guard latency of 0.17 ms. Redundancy-aware optimization reduces average per-instance overhead by more than 90%, to 0.017 ms for hot SQL templates.

Public VR game leaderboards contain tracked motion recordings uploaded by hundreds of thousands of users. Once uploaded, these recordings are accessible to anyone and create privacy risks (i.e., identification and profiling). Prior work has proposed mechanisms that modify tracked movement to reduce these risks. Their utility is commonly evaluated through physical deviation, where smaller deviations indicate better utility, while user studies are less common. However, it remains unclear how well physical deviation explains users' acceptance of a mechanism compared to user studies. We examine this through a user study of three VR motion privacy mechanisms at five physical deviation levels. We find that user studies explain substantially more variation in mechanism acceptance than physical deviation, although physical deviation remains significant. We also find that prior VR experience and exposure to VR privacy mechanisms significantly affect acceptance. We recommend combining physical deviation with user studies and reporting participants' prior experience.

Cloud LLM services typically require users to send prompts to a model provider, creating a privacy risk. Fully homomorphic encryption (FHE) lets a server perform inference without decrypting the input, but representing data as ciphertexts adds storage and computational overhead. In CKKS-based LLM inference, the packing scheme maps logical tensors to ciphertexts and slots. It therefore determines the ciphertext count and the homomorphic cost of linear layers, and it constrains how data pass between linear layers, attention, and nonlinear computation. As models and sequences grow, inefficient layouts accumulate encoding, compute, and layout-conversion overhead. We present Odin, an FHE inference system that co-designs ciphertext packing and model execution for Llama. Starting from a THOR-style baseline whose bottleneck is weight encoding, Odin uses a feature-major cross-layer layout to unify residual connections and layer interfaces, and builds transient intra-operator layouts for linear projections and attention. This reduces redundant plaintext encoding of weights in wide projections. Within attention, QK^T produces scores that Softmax can consume directly, and PV consumes the resulting probabilities, avoiding intermediate repacking. For nonlinear ops, we use minimax polynomial approximation with input-range control and joint error allocation guided by model quality, reducing polynomial degree and multiplicative depth. To our knowledge, Odin is the first open-source end-to-end GPU CKKS implementation of Llama-3. With Llama-3-8B weights and a 128-token input, Odin evaluates all 32 Transformer layers on a single NVIDIA H100 80 GB GPU. Server-side end-to-end FHE evaluation takes 366.4 s and 58.9 GiB peak device memory. Under the same model, input, CKKS parameters, and hardware, THOR takes 1651.9 s, a 4.51x speedup.

Critical-infrastructure knowledge is distributed across heterogeneous, incomplete, and weakly structured evidence, making dependency models difficult to construct automatically and difficult to trust. Large language models (LLMs) can extract structured knowledge from such evidence, but direct LLM-to-graph generation risks unsupported relationships, inconsistent terminology, incorrect entity identities, and erroneous dependency endpoints. We present an evidence-first multi-LLM framework for constructing Infrastructure Knowledge Bases (IKBs) and Infrastructure Dependency Graphs (IDGs) from heterogeneous infrastructure documentation. Multiple open-weight LLMs independently extract candidate entities and dependencies from normalized evidence, after which the framework separates evidence verification, ontology grounding, entity resolution, dependency alignment, validation, fusion, and human review. Evidence support, ontology reconciliation, endpoint resolution, model agreement, and human validation remain distinct states, while provenance and unresolved cases are preserved throughout. The validated IKB is then projected deterministically into the IDG without introducing new LLM-generated knowledge. Evaluation in nine infrastructure projects shows that entity recovery achieves substantially higher recall than complete directed dependency recovery and that canonical endpoint resolution is a major constraint in dependency construction. Cross-model overlap is also much lower for dependencies than for entities, indicating that the models often produce non-overlapping candidate assertions rather than a stable majority consensus. These findings support an auditable evidence-to-IKB-to-IDG process in which uncertainty is preserved and resolved progressively rather than collapsed into a single confidence or voting decision.

Authorship attribution models can re-identify users from seemingly anonymized text by exploiting stable stylistic fingerprints, even after explicit identifiers are removed, posing a growing privacy risk for text publishing and analytics. This risk extends to speech-derived text such as ASR transcripts of meetings and call-center conversations, where stylometric leakage can persist even after acoustic anonymization. Differential privacy-based anonymization often severely degrades text quality and utility. We propose a style-aware, prompt-driven anonymization approach that uses pretrained large language models to construct compact stylistic profiles from minimal samples and rewrite text to suppress identifiable style markers while preserving meaning. Across blog and review datasets, our approach reduces authorship attribution F1 by 60-70% while maintaining content quality and readability, substantially outperforming DP-based and non-DP baselines.