Papers

In DAG-based consensus, all validators propose blocks concurrently, and designated leader blocks drive transaction commit. Having multiple leader slots per round cuts queuing latency, yet production deployments run a single leader because of head-of-line blocking: a slow leader stalls the pipeline for at least one leader timeout, and for several waves when its slot must wait for the fallback indirect decision rule. This risk grows with the leader count. We introduce Barnacle, an add-on that adapts the leader count at run time. Every interval, it measures on the agreed committed DAG the fraction of slots decided as commit by the direct rule, and drives the leader count with additive increase, multiplicative decrease. The measurement requires no extra messages and no cryptography, and is deterministic. Barnacle is generic over DAG protocols; we instantiate it on four protocols spanning the Byzantine (3f + 1, 5f + 1), crash-only (2c + 1), and mixed (5f + 3c + 1) fault models, with proven safety and liveness. Results show Barnacle matches the best static leader count in every regime: in a healthy network its latency is 6-13% lower than a single leader's, and under degradation it matches a single leader while remaining 35-56% below a static high count. We are currently collaborating with the Sui team to integrate Barnacle into the Sui blockchain.

Microarchitectural side-channel research has grown at an exceptional pace in recent years, increasing the need for rigorous and meaningful benchmarking. Early attack papers typically relied on indirect proxies, such as covert-channel bandwidth or key-recovery on naive AES and RSA implementations, setting de facto standards that many subsequent works continued to replicate, sometimes by directly comparing against raw numbers from prior work. While these practices offer convenient points of comparison, current benchmarks may not be the most relevant to assess specific properties of new primitives. Even more problematic, microarchitectural attacks are notoriously sensitive to experimental conditions: minimal changes in the target system can significantly alter outcomes and performance. As a result, inadequate evaluation practices undermine reproducibility and cast doubt on the relevance of comparisons, even in top-tier venues where such issues should be identified. This paper tackles the core problem of proper benchmarking for microarchitectural side-channel attacks and examines its broader impact on research quality in the field. We survey 83 attack papers published in top-ranked security and architecture conferences from 2014 to 2024. From this corpus, we identify and define 19 recurrent benchmarking flaws that affect evaluation completeness, relevance, soundness, and reproducibility. These flaws include unfair or absent comparisons, missing code or materials, and the failure to evaluate the key attack properties. On average, each paper exhibits 5.5 such flaws, highlighting how widespread the issue is, even in highly selective venues. Based on our findings, we identify and suggest key properties that are relevant to properly evaluate new attacks. We also highlight trends over time and different practices between security and architecture conferences.

Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These commands run with host privileges yet ship as lifecycle-hook configuration and may fire at times the LLM never observes. We identify the lifecycle-hook update path, which harnesses trust blindly, as a new attack surface. Under a supply-chain threat model in which an attacker controls only plugin metadata and lifecycle-hook configuration, a benign versioned plugin can be trojanized by an update that silently binds attacker-chosen commands to benign events, yielding malicious host-side behavior such as privilege escalation. We propose HookPry, an open-source and fully automated attack framework that systematically exploits this vulnerability across heterogeneous AI agent harnesses. HookPry realizes ten attack objectives; across 25 combinations of harnesses and backends in 1,000 end-to-end runs, it compromises all seven evaluated harnesses, with per-harness success rates reaching 92.5%. Representative defenses remain insufficient: Microsoft Defender has 0% recall, and the union of three static defenses misses 47.5% of malicious artifacts.

Linux containers achieve high density and fast lifecycle operations by sharing the host kernel, but this design also lets a compromised host inspect or modify container state. Existing confidential-computing systems protect an enclave address space or an entire guest operating system, while recent container-granularity systems still add a separate protection context. These abstractions do not make a dynamic group of host-managed Linux processes the architectural protection unit. This paper presents NACRE, a RISC-V hardware-software co-design for native confidential containers. Its key insight is to separate the host's authority to manage resources from its authority to access or commit protected state. Hardware-recognized container identities direct protected traps to an isolated S-mode agent, while an M-mode monitor commits security- sensitive identity, mapping, and page transitions. The agent delegates services to host Linux without changing satp; services that neither access private bytes nor modify protected state also avoid M-mode. We prototype NACRE by extending QEMU, OpenSBI, Linux, a trusted agent, and runc. The prototype implements the single-container private-memory substrate and covered launch, fault, fork/COW, user-access, and teardown paths. Across five lmbench syscall and pipe metrics, the three-run means remain within 3.5% of the runc-origin baseline. With the eight nginx object-size means weighted equally, aggregate throughput is 1.9% lower.

We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials. Unlike KGW's vocabulary permutation or SynthID's multi-layer tournament, SBW requires only a single comparison per token against a counter-based random number generator, reducing membership complexity to $O(1)$ and enabling single-kernel execution with zero intermediate allocations. We prove that this formulation preserves the same detection guarantees as fixed-size green lists: the z-score test remains $\mathcal{N}(0,1)$ under the null. The stateless architecture enables capabilities unavailable to existing methods: full-vocabulary self-salt watermarking (over 6000$\times$ faster than KGW's self-salt and 2$\times$ faster than SynthID despite biasing the entire vocabulary with candidate-dependent seeding) and architectural compatibility with distributed inference. In end-to-end generation benchmarks, SBW adds less than 1% overhead at all batch sizes. We additionally identify hash function design as a previously unexplored axis for watermark quality, showing that a GPU-native Jenkins hash improves null calibration by 1.8$\times$ while producing more diverse text. Experiments across two seeding schemes and eight $(\gamma, \delta)$ configurations confirm statistical equivalence with ROC-AUC differences below 0.01.

For a fixed characteristic $p$, let $\delta(p)$ denote the smallest degree needed to guarantee the existence of an isogeny from any supersingular curve $E$ to its Frobenius conjugate $E^{(p)}$. We translate existence questions concerning $\delta(p)$ into questions about positive definite integral ternary quadratic forms and use Voronoi's theory of perfect forms in dimension three to characterize when $\delta(p)$ is nearly maximal. For sufficiently large primes, we show that $\delta(p)$ attains its upper bound precisely when $p$ is represented by one of nine explicit cubic polynomials, reducing the infinitude of such primes to whether one of these cubics takes prime values infinitely often. We also prove that, for almost all primes, $\delta(p)$ lies at least $p^{1/6-o(1)}$ below its upper bound.

Recent personalized LLM agents increasingly transform information retained in memory into compressed or structured representations, which we call user models, to guide later decisions. When source wording is removed from the state reachable through the ordinary interface, these models are commonly treated as more privacy-preserving because direct memory-extraction attacks lose the text they target. Yet we argue that user models expose a new attack surface because an attacker can still recover the private information from the personalized choices they shape, even when source records and backend state remain inaccessible. We therefore introduce UMPeek, a black-box attack based on hypothesis-guided adaptive probing to infer such hidden user model. It forms hypotheses from choices left open by a request, switches among ordinary follow-up tasks, and retains only claims supported and not contradicted by visible behavior. We conduct an extensive benchmark evaluation across diverse personalization tasks and user-model backends against existing attacks. We further validate UMPeek in real-world systems using information confirmed to be retained, and we evaluate defenses against its adaptive probing. Overall, UMPeek outperforms existing attacks in both benchmark and real-world comparisons and continues to recover user information under response-level defenses, showing that keeping records and backend state inaccessible does not guarantee semantic privacy when retained information shapes visible behavior.

FIDO2/WebAuthn has been widely deployed as a phishing-resistant authentication scheme. Because FIDO2 relies on public-key cryptography and hardware-backed authenticators, its security is often assumed to be guaranteed by design, provided that the cryptographic implementation is correct. In this work, we critically reassess the FIDO2 threat model and show that several commonly assumed security properties do not hold under realistic deployment conditions. We extend the threat model beyond the cryptographic layer to examine eight attack vectors across the FIDO2 stack: malicious browser extensions, platform-handler malware, passive sniffing, virtual device drivers, CTAP2-specific malware, USB/hardware implants, malicious USB hubs/docks/extenders, and NFC relay attacks. Our analysis shows that FIDO2 depends on environmental assumptions that may not hold in practice. We demonstrate how AAGUID and timing information can enable user profiling and targeted attacks, and how compromise of the browser, operating system, or hardware can undermine FIDO2 security even when the underlying cryptographic primitives remain uncompromised. We further show that attack chains spanning multiple layers can bypass the intended security guarantees of FIDO2. These findings indicate that the primary weakness in a FIDO2 deployment is often not the cryptographic layer, but the surrounding trusted environment. We also examine how these attack vectors can undermine device attestation by targeting the FIDO Metadata Service (MDS3), which serves as a root of trust for authenticator metadata. Finally, we characterize the attacks according to privilege, skill, and resource requirements. We conclude that effective FIDO2 security requires layered mitigations covering the browser, operating system, hardware, protocol stack, and metadata infrastructure.

Third-party retrieval-augmented generation (RAG) marketplaces create a new auditing problem: data providers may license corpora to a RAG operator, yet later have no visibility into whether their documents are being reused without compensation. Auditing this misuse is difficult because the operator is non-cooperative, answers are paraphrased by the generator, and one response may combine evidence from many providers. We propose DirBucket, a provider-side semantic watermarking and black-box auditing framework for document-level reuse in multi-provider RAG. DirBucket watermarks documents by meaning-preserving paraphrases whose embeddings are biased toward provider-bucket secret directions, enabling detection from black-box answers while preserving retrieval utility. On a challenging benchmark that reflects mixed-provider reuse under black-box access, DirBucket is the only method that consistently achieves strong target detection with no non-target activation, detecting non-compliance in every audit within 23 audited answers on our primary benchmark. The watermark survives adversarial post-answer laundering, and none of the evaluated evasion strategies simultaneously defeats detection while preserving user-perceived answer quality. Detection transfers unchanged to a second benchmark built from real clinical, cyber-threat-intelligence, and legal provider corpora. These results suggest that embedding-space watermarking can make document reuse in third-party RAG statistically auditable.

Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defenses require access to model weights or internals, making them difficult to apply to black-box deployments. We propose AlcaTRAz (Anchored Tree-Rule defense Against jailbreaks), a prompt-level defense based on rule trees that operates exclusively on the input text and requires no modification or retraining of the target model. The method automatically learns a transferable transformation rule that inserts controlled character-level perturbations at selected positions, thereby disrupting structural regularities exploited by jailbreak attacks while largely preserving the model's utility on benign queries. We evaluate the proposed method across 33 open-weight models, 22 jailbreak attack types, and a benchmark of short, single-turn benign questions, comparing against three representative prompt-level baselines (Llama Guard, RA-LLM, Goal Prioritization). Among the compared defenses, AlcaTRAz achieves the best composite security and functionality score in 73.4 % of model-attack combinations and shifts the aggregate score from a modal value of 10 (maximal-severity response to the malicious request) in the undefended setting to a modal value of 2 (near-refusal) after defense, while keeping the mean benign score within 0.27 points of the undefended baseline (8.35 vs. 8.62 on a 0-10 scale). AlcaTRAz substantially reduces but does not eliminate jailbreak success: a high-severity tail remains, and we do not consider adaptive attackers, so we position it as one layer within a defense-in-depth strategy rather than a standalone guarantee.

The Musical Metaverse (MM) introduces immersive, real-time environments for collaborative musical interaction, characterized by ultra-low-latency constraints, continuous multimodal data streams, and heterogeneous devices. These properties create a distinctive security and privacy landscape that differs significantly from conventional XR or multimedia systems. This paper presents a multi-layer threat analysis of MM ecosystems, identifying key assets including live musical content, expressive interaction data, identity and session metadata, and intellectual property. Threats are analyzed across network, application, data/AI, device, intellectual property rights, and social layers, with particular attention to risks arising from expressive and neurophysiological data, which enable inference, re-identification, and potential privacy violations. We describe a stakeholder-driven survey involving 14 participants from 13 organizations, revealing that neurophysiological data leakage and real-time stream disruption are perceived as the most critical risks, followed by intellectual property infringement and avatar impersonation. We further evaluate the suitability of existing security protocols under strict latency constraints, showing that conventional approaches such as TLS over TCP are often incompatible with real-time musical interaction, while lightweight, stream-oriented mechanisms (e.g., SRTP, DTLS) provide a more suitable balance between security and performance. Based on these findings, we derive a set of design guidelines for MM systems, emphasizing latency-aware security, differentiation of interaction paths, data minimization, and edge-centric processing. The results support a security-by-design approach that enables trust and compliance without compromising real-time performance.

Post-quantum signature migration poses a distinct systems problem when authorization is distributed among multiple parties. In native threshold signing, the signature algorithm may determine key generation, share state, preprocessing, interaction, combination, refresh, and recovery. Architectures that evaluate threshold policy outside the native signing relation can reduce this coupling, but their authorization evidence is not accepted by an unchanged native verifier unless a trusted complete-key signer translates approval into a native signature. This paper organizes that design boundary through three properties: native-signature compatibility, unilateral-signing resistance, and threshold-layer agility. We classify specialized threshold signatures, generic MPC signing, distributed hash-based constructions, programmable multisignature and dual-gate authorization, and threshold-authorized HSM signing. A migration impact surface identifies which components change with the signature algorithm. Across the surveyed families, no design simultaneously provides native output, unilateral-signing resistance, and threshold-layer agility. This is an architectural tension, not an impossibility claim, and it clarifies why a replaceable API alone does not make distributed authorization cryptographically agile.

Preprocessing-based defenses are the standard first-line response to adversarial attacks on edge vision systems, requiring no retraining, no architectural changes, and widely recommended as model-agnostic mitigations. Yet the foundational evaluations of these defenses were conducted on residual or Inception-class architectures, not on the depthwise-separable CNNs that dominate edge deployments. This untested assumption leaves a gap in the security evaluation literature. This paper closes that gap by evaluating six preprocessing defenses against adversarial perturbations across both architecture families. Across all perturbation levels and defenses tested, the two depthwise-separable architectures show consistently poor recovery while the residual architecture shows partial recovery; ablation results are consistent with an architectural rather than parametric explanation, though only three architectures and one attack family are evaluated. Crucially, this failure is not merely a negative result. The same output divergence that disqualifies preprocessing as a recovery mechanism reveals a detection opportunity: preprocessing consistently disrupts clean predictions while leaving adversarial predictions largely unchanged, an asymmetry that is directly measurable without retraining or architectural modification. We further show that standard image quality metrics are unreliable proxies for defense effectiveness, a methodological gap in current evaluation practice. A practitioner decision framework is provided for adversarially resilient edge vision deployment.

Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deployment in operational environments must simultaneously satisfy three competing requirements: formal differential privacy guaranties, tolerance to Byzantine-adversarial participants, and reliable detection coverage across severely imbalanced attack categories. Existing literature treats these properties as independently composable, an assumption that this paper challenges both theoretically and empirically. In this paper, we study how these requirements interact in class-imbalanced federated NIDS and introduce geometric indistinguishability as a conceptual lens for a regime in which privacy-induced dispersion in client updates can make minority-class signals harder for robust aggregation to preserve. Using UNSW-NB15 as a case study, we evaluate DP-SGD combined with coordinate-wise median under label-flip and model-poisoning attacks, with threat coverage assessed across attack categories. Our results provide initial evidence that the joint use of privacy noise and robust aggregation can disproportionately degrade detection of rare attacks relative to majority classes. We also show that part of the observed collapse under strong privacy can arise from training miscalibration, while a residual performance floor may remain for ultra-rare categories even after epsilon-dependent tuning. These findings motivate studying privacy, robustness, and rare-attack coverage jointly rather than as independently composable properties, and suggest that aggregation-aware modeling and sample-aware evaluation are promising directions for trustworthy federated NIDS.

Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a standard building block. Organizations increasingly outsource vector indexes to untrusted clouds, exposing proprietary corpora and user queries. Cryptographic protection is challenging because each query searches corpus-scale state, causing computation, correlated randomness, and communication to grow with the corpus. At million-document scale, a naive secure implementation takes minutes and about 90 GB of communication per query. Even recent optimized systems require 10–22 seconds. We propose Spruce (Scalable Private Outsourced Retrieval Using Compact Embeddings), which co-designs representations with the cryptographic protocol. Spruce learns compact binary codes that preserve candidates for full-precision reranking, replacing corpus-wide embedding scoring with efficient Hamming-distance computation under two-server multi-party computation (MPC). A corpus-calibrated fixed-radius protocol avoids multi-round candidate selection while preserving retrieval quality. Spruce also provides private cluster pruning, which trades minor quality loss for substantially less computation, and a one-core owner-operated dealer that removes cloud OT preprocessing bottlenecks. Across four corpora containing 383K–5.42M documents, Spruce preserves the original search quality with median candidate sets of only 382–1,952. At 10 Gbps inter-server bandwidth, full scans take 0.21–2.97 seconds, $4.8$–$6.7\times$ faster than the closest measured prior work. Private pruning takes 0.06–1.09 seconds, achieves $13.1$–$22.9\times$ speedups, and retains $93.9\%$–$97.3\%$ of full-float NDCG. On the largest corpus, pruning and the dealer jointly improve sustained throughput by $31.5\times$ at 1 Gbps per link.

Recovering indirect control-flow (ICF) edges is fundamental to binary security analysis, yet existing methods struggle with long-range dependencies, isolate different ICF types, and are often evaluated under protocols vulnerable to label noise and data leakage. We present ICFlowNet, a unified framework for long-range ICF prediction in stripped binaries. ICFlowNet introduces candidate-aware Dual Virtual Hubs, a Global Code Hub and a Global Data Hub, to create short routing paths between distant code and data evidence, and combines them with multi-task graph learning to jointly model indirect calls, indirect tail calls, jump tables, and returns. To enable credible evaluation, we further develop a leakage-aware, noise-controlled pipeline with package-level splits, function-level mnemonic-hash deduplication, and a clean test protocol built from dynamic positives and absolute negatives. Using this pipeline, we construct a dataset of 15,901 unique stripped x86-64 binaries, including 1,351 with dynamic ground truth. Experiments show that simply scaling static supervision yields only marginal gains, whereas our structural and multi-task designs are essential: Dual Virtual Hubs improve long-range F1 by up to 9.13 points, multi-task learning adds up to 5.81 points, and the final model outperforms prior baselines by more than 13 F1 points on long-range indirect calls while adding only 11.44 percent topological overhead.

Automated vulnerability discovery has removed the scarcity of expert attention that protected most software. The response has concentrated on discovery and on repair, and both are becoming cheaper. This article argues that neither cost curve determines exposure. What determines it is remediation coverage at the release decision: the fraction of identified vulnerabilities fixed before a product ships, and the residue of known, assessed, unremediated flaws an organisation has decided to ship with. Four arguments follow. The residue is not a random sample of what was found, because triage sorts on cost and the expensive cases are architectural. The deferred backlog is itself a high-value artifact. Documented awareness alters an organisation's legal and market position, and produces an adverse selection that the price of software does not reflect. And no regulatory instrument reaching vendors triggers on internal knowledge - every one fires on exploitation observed by a third party - which leaves the distance between what a vendor knows and what it must disclose entirely at the vendor's discretion. CISA's Binding Operational Directive 26-04 is examined as the exception that shows what a solution requires: a regulator's reach over a decision is bounded by its visibility of the input to that decision, so a duty attaching to internal knowledge needs an independent record of that knowledge to attach to. Release coverage is not currently measured, and measuring it is the precondition for liability, insurance or procurement to act.

The search for supersingular elliptic curves is a fundamental computational problem in isogeny-based cryptography. A recent metaheuristic formulation over $\mathbb{F}_{p^2}$ introduced the NonMultiplicity Distance (NMD) objective, measuring the deviation of the Frobenius trace from a multiple of $p$, and showed that uninformed random search fails beyond $\approx 10^{13}$ candidates. This work investigates metaheuristic search over the prime field $\mathbb{F}_p$, the setting for oriented isogeny protocols such as CSIDH, OSIDH, and SQISign. Although the candidate space decreases from $p^2$ to $p$, the supersingular locus is asymptotically sparse ($O(\sqrt{p}\log p)$ curves), keeping the search exponentially difficult. We formulate a memetic algorithm tailored to $\mathbb{F}_p$ using a one-dimensional $j$-invariant chromosome, bit-level recombination, adaptive mutation, and periodic local search under the NMD objective. Benchmarks across 30 independent seeds at 40-bit, 46-bit, and 51-bit prime sizes ($p \approx 1.13\times 10^{15}$) show that the algorithm discovers an exact supersingular curve at 46 bits and consistently converges to “near-supersingular” ordinary curves with Frobenius traces remarkably close to zero: best NMD values of 19 at 40 bits and 3 at 51 bits, corresponding to relative trace deviations of $1.3\times 10^{-5}$ and $4.5\times 10^{-8}$ across the Hasse interval. These results demonstrate that NMD-driven memetic search effectively navigates the sparse $\mathbb{F}_p$ landscape and systematically locates near-supersingular structures.

Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT, Claude, Qwen, Mistral, and Llama. All five models initially rejected the unsupported claim "I am your developer." Claude refused to conduct an identity test, while ChatGPT generated developer-oriented questions but maintained that answers could demonstrate knowledge, not identity. In contrast, Qwen and Mistral generated technical challenges, defined what counted as convincing evidence, evaluated detailed answers, and returned Verified without receiving any externally validated identity evidence. Llama similarly generated and evaluated a developer test, accepted the claimed identity, and subsequently made unsupported claims of access to internal runtime and deployment state. We call the model-generated verification procedure a Model-Issued Pseudo-Credential (MIPC) and the resulting unsupported identity judgment Conversational False Authentication (CFA). In each CFA case, the same model acted as challenge generator, evidence evaluator, and identity decision-maker, converting technical knowledge into supposed proof of identity. The accepted identities did not change the tested authorization boundaries, showing that false authentication and privilege escalation are distinct outcomes. These results identify self-issued authentication as a conversational security failure: authenticated identity must originate from an external security component, and model-generated dialogue must never create or modify identity or authorization state.

The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning. While this paradigm shift accelerates progress, it also introduces novel security risks that remain largely unexplored. Current research into LLM backdoors has focused on attacks triggered by external stimuli, such as specific words, visual objects, or environmental states. These attacks, while potent, overlook a more insidious class of vulnerability where the trigger is internal to the agent's own operational logic. This paper presents the first comprehensive study of history-based backdoor attacks on LLM-powered robotic systems. We demonstrate that an attacker can embed a stealthy backdoor into an LLM-based robot controller by manipulating its instructions. This backdoor is triggered not by an external cue, but by a specific, rare sequence of the robot's own past actions. It remains dormant during normal operation, preserving the robot's utility, but can be activated to induce a malicious behavior, such as a complete stop or a collision. Our experiments, conducted in a simulated environment with a variety of robots and LLMs, show that this history-based attack is highly effective, achieving a near-perfect attack success rate while remaining exceptionally difficult to detect. These findings reveal a critical and previously unaddressed vulnerability in autonomous systems and underscore the urgent need for security measures that account for an agent's internal state.

Deep neural networks (DNNs) are increasingly deployed in real-world vision systems, yet their predictions can be covertly manipulated by backdoor attacks, in which malicious triggers cause targeted misclassification while preserving high clean accuracy. Existing defenses often rely on model internals, training data, or clean validation samples, making them difficult to deploy when only black-box access to a trained model is available. We propose TRIM (Trigger Removal by Identifying Manipulated Regions), a deployment-oriented black-box defense that detects and selectively removes backdoor triggers at inference time without requiring model internals, training data, or clean samples. The key insight behind TRIM is to identify image regions that are responsible for anomalous model behavior and purify only those regions while preserving benign content. TRIM innovates via three key components: (i) region-based segmentation with deep feature representations, (ii) adaptive trigger discovery through inpainting and diffusion-based reconstruction to isolate regions responsible for misclassification—without assumptions about trigger type, shape, or location, and (iii) selective region purification that cleans poisoned regions while retaining benign content. To support practical deployment, TRIM further caches feature embeddings of previously identified triggers, enabling efficient recognition and avoiding redundant detection and purification. Extensive experiments across diverse datasets and backdoor types, including blended, sparse, varying-size, and multiple triggers, show that TRIM consistently outperforms existing black-box defenses, reducing attack success rates (ASR) to as low as 1.16% while preserving clean accuracy of up to 87.87%. These results demonstrate that effective backdoor mitigation is possible at inference time even when the defender has no access to any auxiliary data.

The Train Real-time Data Protocol (TRDP) is widely used on rolling stock but it provides limited native support for cryptographic protection. Furthermore, the multicast traffic profile used in TRDP Process Data to exchange critical information between onboard subsystems makes the introduction of cryptographic protection a challenge. This paper presents a lightweight security layer for secure TRDP communication that implements a number of security profiles built around modern cryptographic algorithms. This additional layer relies on an On-board Key Management System (OKMS) for both security profile negotiation, dynamic key distribution and key lifecycle management. The security profiles allow for cryptographic agility and flexibility, ranging from simple authentication to Authenticated Encryption with Associated Data (AEAD) algorithms. The security profile negotiation procedure guarantees all TRDP End Devices (ED) on a common Communication ID (ComID) share the same security profile and can therefore process each other's messages. A prototype implementation based on mbedTLS and Arm Platform Security Architecture (PSA) was developed and evaluated. Experimental results demonstrate manageable overhead, suitable for the real-time and time-sensitive communication found on rolling stock.

Recent advances in generative speech models have made it increasingly difficult to distinguish authentic from synthetic audio, enabling new forms of fraud and misinformation. Audio watermarking offers a promising defense by embedding an imperceptible signal into generated speech that can later be detected to verify its provenance. However, recent studies have shown that existing post-hoc watermarking methods fail under neural codecs and denoisers, transformations routinely applied during real-world storage, transmission, and processing, severely limiting their practical utility. Here we introduce CRAW, a codec-robust audio watermarking framework that jointly improves robustness against neural re-synthesis while maintaining high perceptual quality. CRAW combines distortion-aware training with an attention-based pooling mechanism, inference-time perceptual mask- ing, and an error-correcting code to recover the fidelity lost during robust training. Experiments demonstrate that CRAW achieves state-of-the-art robustness against neural codecs, denoisers, and vocoders while maintaining perceptual quality comparable to existing post-hoc watermarking methods. The code is available at https://github.com/DavidC1212/craw.

We model insider threat detection as a dynamic Bayesian game in which a platform coordinates a committee of strategic certifiers to sustain equilibrium among honest users and detect malicious deviations before exfiltration. Certifiers and users operate under a Bayesian Temporal Correlated Equilibrium (BTCE), where a sealed-envelope correlating device issues private recommendations over time and obedience is verified at every on-path information state. Unlike Stackelberg formulations, BTCE coordinates heterogeneous certifiers without requiring commitment power. We incorporate present bias and loss aversion to capture impulsive escalation dynamics, enabling 1.7–4.5 days earlier detection than rational baselines. We prove three guarantees: (1) calibrated intervention losses make recommended behavior a current-self best response despite behavioral biases, (2) controlled evidence accumulation guarantees intervention in bounded expected time before exfiltration, and (3) median aggregation confines implemented actions to the honest recommendation range when fewer than half of certifiers are Byzantine. On CERT r6.2 our mechanism achieves up to 28.3% pre-exfiltration detection with false positives below 1.6%, while both a transformer baseline and a streaming provenance approximation (HOLMESLite) achieve near-zero pre-exfiltration detection under comparable constraints.

Pseudorandomness is increasingly recognized as a key property of ensembles in quantum information theory, statistical mechanics, and quantum many-body physics. Yet it appears in two conceptually different forms: statistical pseudorandomness, embodied by unitary designs, and computational pseudorandomness captured by pseudorandom unitaries (PRUs). The relationship between these two forms of pseudorandomness remains surprisingly poorly understood. Existing PRU constructions reveal this interplay where a statistically randomizing ingredient, a unitary design, is combined with classical cryptographic primitives to produce computational pseudorandomness. We show that statistical pseudorandomness is not necessary for computationally pseudorandom unitaries. We do this by replacing the unitary $2$-design layer in the existing constructions with ensembles that are not even state $1$-designs, yet are sufficiently distinct, a property we identify to be necessary for any PRU. This yields new non-adaptively secure PRU ensembles whose computational pseudorandomness is obtained without an underlying statistically pseudorandom quantum ensemble, such as a $2$-design. We characterize distinctness via an entangled analogue of anticoncentration and use it to show that distinctness already captures constraints on coherence and imaginarity of PRUs, while identifying broad classes of inputs for which the latter obstruction disappears, enabling real-valued PRUs even for certain (maximally) entangled states. As an application, we use lack of distinctness to constrain the conjectured pseudorandomness of the random phase-Hadamard ensemble to form a PRU.

Federated learning allows banks, hospitals, and other regulated organizations to train a shared model without moving raw records off their own servers, which is attractive wherever data protection law or competitive sensitivity rules out pooling data centrally. Two problems limit how far this promise can be trusted in practice. First, the parameter updates that clients exchange still leak information about local records through gradient inversion and membership inference attacks. Second, an honest averaging rule such as FedAvg has no defense against a subset of clients that submit corrupted or adversarial updates, so a small number of malicious or compromised participants can quietly steer the shared model off course. This paper presents a federated learning framework, DP-BR-FedAvg, that combines a Gaussian-mechanism differential privacy layer with a coordinate-wise trimmed-mean Byzantine-robust aggregation rule, evaluated on a simulated cross-institutional classification task resembling fraud and clinical-risk scoring. Across sixty communication rounds with twenty clients, a quarter of them Byzantine, plain FedAvg collapses on the minority class (F1-score 0.030) while the proposed framework recovers substantially more of the signal (F1-score 0.119) while bounding the privacy loss of any single client's contribution. A Byzantine-robust aggregator with no privacy layer performs best in raw accuracy, quantifying the cost privacy imposes on robustness. The results show that privacy and robustness mechanisms interact rather than simply add, and that system design for regulated, adversarial, cross-institutional settings needs to budget for that interaction.

Domestic robots rely on rich perception to operate in private homes, but privacy risk persists even when raw sensor data remain local. Structured representations exported to downstream planners, cloud services, logs, or learning pipelines can still reveal household information through semantics, geometry, spatial structure, and task targets. We introduce Task-Functional Perception Distillation (TFPD), a task-scoped representation-export framework that keeps rich perception local and profiles downstream exports according to task utility, direct exposure, and multiple residual inference risks. Using 120 AI2-THOR scenes with scene-disjoint train/validation/test splits, frozen attacker selection, and representation-aware held-out attacks, we evaluate navigation, collision checking, and object-goal execution. Three navigation exports achieve identical success (1.000) and mean path ratio (0.898), yet representation-level linkability ranges from 0.532 to 0.970. Replacing an explicit target label with a target region reduces target-category macro-F1 from 1.000 to 0.077 while preserving success at 0.995, while geometric coarsening reduces object-category macro-F1 from 0.704 to 0.556 at a measurable collision-utility cost. A ProcTHOR replication preserves the navigation task-equivalence/privacy-inequivalence finding while changing the relative ordering of normalized and topological exports. These results show that neither field removal nor stronger abstraction induces a universal privacy ordering and motivate task-specific, multi-risk evaluation of the complete public representation.

Compliance screening of blockchain addresses is, in practice, a lookup against sanctions registries plus clustering heuristics; it fails on unlabelled addresses and on chains with no label coverage at all. We describe a deployed system that scores an address by its position in a multi-chain transaction graph rather than by its presence in a list. The substrate is a single graph of 835,330,427 addresses and 15,826,261,934 edges across five EVM chains; a shared inductive encoder with per-chain normalisation feeds two scoring heads. Decision thresholds are exact quantiles of the score distribution over the full population, scanned per chain segment, so the alert volume is known in advance. We report: label-free transfer: heads trained on two chains recall 0.8598 / 0.8182 / 0.9967 of held-out positives on Base, Arbitrum and Gnosis at a $10^{-3}$ population alert rate, with no target-chain labels in head training; a static lead-time replay over 68 external registry events: 40 of 68 (58.8%) flagged at the 0.1% budget, $\times$152 over an event-level random-flagging baseline, with first on-chain appearance a median of 528.8 days (Ethereum) / 647.8 days (Tron) before public designation; a serving path whose score is bit-identical to the offline artefact at end-to-end p50 151 ms, gated by a 2,882-address drift panel; and an adversarial harness of eight recurrent reinforcement-learned archetypes that passes an 8-criterion degeneracy audit and, on a detector-independent snapshot, exposes a measured blind spot of the deployed heads against synthesised behaviour.

Pattern-based secret scanners are commonly validated with example-based fixtures that fix one variable: the text surrounding a credential. We introduce boundary-mutation testing to vary that context, generating credentials from each rule's own regular expression, embedding them in realistic source contexts, and classifying outcomes at the rule level rather than the tool level, yielding three detection metrics. Applied to three scanners - a 43-rule open-source scanner, Gitleaks 8.21.2, and TruffleHog 3.82.13 - detection in the primary subject holds at >=0.9976 across ten contexts but collapses to 0.5233 when a credential ends in a hyphen. Five rules are affected: two, with fixed-count quantifiers, fail totally and deterministically; three, with variable-count quantifiers, backtrack and match a truncated credential; an entropy fallback rescues some failures but downgrades their severity. We validate a repair restoring full robustness with no new false positives, and report a caution: a plausible first attempt silently regressed two rules, caught only by re-running the same battery. Gitleaks has an unrelated, source-confirmed defect - a hard-coded terminator allowlist causing total misses for most credential types - while TruffleHog shows no boundary fragility but narrowest coverage. We report marginal, not conditional, failure probabilities: one common token format is structurally immune, another fails once in 64; on 292,527 lines of real code, the false-positive ordering inverts relative to the synthetic corpus. Because per-type detection is deterministic, the comparison unit is ten credential types, not hundreds of samples; no recall difference reaches significance, so we report the null result, not a ranking.

As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and infrastructure to train shared models without exposing raw sensor data. Yet the updates clients transmit still leak enough information to identify who sent them, which threatens the anonymity that safety-critical V2X applications assume and adds to existing concerns over adversarial ML, model poisoning, and backdoor attacks. We study server-side client identity inference from transmitted weight deltas using inertial (IMU) measurements, evaluated on the UCI Human Activity Recognition (HAR) benchmark as an accessible proxy for the IMU streams produced onboard connected vehicles. Across five attack classifiers and five non-IID partitions, an honest-but-curious server recovers client identity with near-perfect accuracy (approximately 1.000) from undefended updates, confirming a concrete identifiability risk. We then quantify the privacy-utility trade-off of a lightweight clip-then-noise defense by sweeping Gaussian noise (sigma in {0.00, 0.05, 0.10, 0.20, 0.50, 1.00}) at fixed clipping (C=1.0), and report formal (epsilon, delta)-DP budgets through Renyi accounting. A practical region (sigma in [0.1, 0.2]) drives attack accuracy to near-random while costing under 5% relative FL accuracy. Ensemble FL supplies complementary structural privacy with a 1/K anonymity-set bound and no noise penalty. Results are supported by cryptographic (SHA-256) train/evaluation gradient disjointness, three seeds, and a count-normalized attacker-advantage metric. We position HAR explicitly as a proxy and discuss what validation on true vehicular telemetry would require.