Papers

This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and video calls. Instead of passively searching for artifacts, DF-CAPTCHA prompts the caller to perform simple challenge-response tasks that are easy for humans but difficult for current real-time deepfake systems to generate convincingly. The framework verifies the response using four criteria: realism, identity consistency, task completion, and response time. We evaluate the approach across both audio and video modalities using user studies and experiments with real-time deepfake models. Results show that people often struggle to distinguish real-time deepfakes from authentic media, while DF-CAPTCHA substantially improves detection performance over passive methods, reaching high accuracy in both modalities. These findings suggest that active challenge-based verification is a practical and robust defense against next-generation social engineering attacks based on real-time deepfakes.

Emil Post's productive sets are not even semi-computable, let alone computable, being thus essentially incomputable. Accordingly, formal languages whose set of words is a (completely) productive set are essentially undecidable. In this article, I elaborate on Post productivity from the viewpoint of formal language theory: I design formal grammars that emulate the construction of productive sets of natural numbers and are thus beyond Turing-decidability.

Anomaly-based network intrusion detection systems (NIDS) are an important first line of defense. However, training NIDS for new attack types is challenging, because labeled attack data are rarely available. Few-shot learning (FSL) addresses this problem by learning from few samples. However, the approaches and evaluation settings, that have been investigated so far, vary widely. This work systematically reviews FSL approaches for NIDS published from 2022 to 2026. We conduct a systematic literature review with PRISMA 2020-like reporting to search ACM Digital Library, IEEE Xplore, and Scopus. From a set of 1,358 initial records, we retain 21 studies after screening, deduplication, and quality filtering. We classify the applied FSL approaches, datasets, and experimental parameters and compare reported performance. Meta-learning and convolutional neural networks are the most common approaches, with 8 and 10 studies, respectively. Most studies evaluate five or fewer samples per class, although settings vary. CIC-IDS2017 and CSE-CIC-IDS2018 are the most frequently used datasets. Missing parameters and source code limit reproducibility and direct comparison between approaches.

As AI systems move from transient model invocations toward long-lived actors that persist across credentials, clients, sessions, and runtime instances, identity infrastructure must answer a basic question: where should the canonical continuity boundary be placed? This paper introduces Actor-native Identity and presents SoulAuth, an open-source Rust reference implementation for Humans and long-lived AIActors. We argue that any subject that must persist under its own identity and remain independently attributable should have an ActorIdentity that is not replaced by an Account, Credential, Client, AuthSession, IdentityBinding, or runtime instance. SoulAuth therefore treats Humans and long-lived AIActors as first-class identity subjects while keeping authentication distinct from downstream authority. Methodologically, we use a Philosophical Engineering approach that translates conceptual analysis of subjecthood into identity objects, invariants, lifecycle semantics, system responsibilities, implementation boundaries, and inspectable conformance evidence. Evaluation against the fixed SoulAuth v0.1.0 artifact shows that the implementation realizes core boundaries including Human/AIActor first-class identity status, Client/Actor separation, and Authentication/Authority separation, while gaps remain in unified Credential modeling and historical attribution anchored to ActorIdentity. We therefore report partial, not full, architecture conformance.

A block typically changes only a small fraction of blockchain state, yet producing a state root makes validators update an authenticated tree spanning it all. We show how to support verifiable reads from the writes alone. We introduce Block Update Digests (BUDs), that commit to a block's writes and link each key touched in that block to its previous modification. An optional prior-value record lets one successor BUD authenticate the value between modifications, replacing the baseline's two BUD openings. SuperBUDs summarize those writes over longer intervals, letting a reader verify that a value remained unchanged without checking every intervening block. Thanks to BUDs and SuperBUDs, validators can just keep ordinary flat state while still serving proofs of current and historical values, including deletion. We prove soundness and completeness for reads at or after a key's first logged modification when the required proof data is available. In experiments with the baseline format, a 50x increase in state size raises the measured base-BUD cost by just 1.24x. In paired QMDB experiments, lowering its garbage-collection activation threshold raises process CPU time by 1.3-2.7x and device bytes written by 1.6-2.4x relative to its dormant configuration. BUD authentication requires no corresponding relocation of live entries. In the evaluated baseline, two-digest read-layer payloads stay below 800 bytes, and warm hash-path verification takes at most 146 {\mu}s at p99. Authenticated reads need not make validators maintain an authenticated tree over the entire state.

Web measurement studies rely on domain datasets such as Tranco to quantify the prevalence and impact of security issues at scale, but exhaustively analyzing these datasets is often infeasible because of the cost of advanced analysis techniques, requiring the use of sampling. Despite its widespread use, sampling remains largely guided by convention—most commonly \emph{Top $N$} domain selection—rather than evidence, and its influence on the validity and generalizability of security findings has received little systematic evaluation. Consequently, it remains unclear whether common sampling strategies introduce systematic bias, distort observed vulnerability rates, or limit comparability across studies. In this work, we undertake, to the best of our knowledge, the first comprehensive investigation into how sampling methodologies affect the measurements and the conclusions. Through a comprehensive literature review and large-scale measurements of 500k Tranco and 24.8M Common Crawl hosts, we perform a comparative evaluation of datasets and sampling strategies. We show that, while Top $N$ sampling may be a rational strategy, the researchers have to bear in mind that Top $N$ does not reflect the overall distribution of the web. Instead, probability-based strategies yield stable, unbiased estimates for prevalence and many impact objectives. Hybrid sampling provides no advantages over pure probability sampling, as its deterministic prefix consistently contributes negatively to accuracy. Building on these results, we provide data-backed guidance for future studies, proposing to use an adaptive probability-based sampling strategy that remains effective even when the prevalence of the target issue is unknown.

Digital payment infrastructures increasingly provide adolescent users with direct access to real-time financial services. While early access promotes financial literacy and digital inclusion, it exposes young users to severe risks of impulsive spending, social engineering frauds, unauthorized transactions, and merchant exploitation. Conventional countermeasures rely on probabilistic machine learning or rigid static controls. However, allowing probabilistic or generative artificial intelligence (AI) models to directly influence real-time payment authorization introduces non-determinism, unpredictable edge-case behavior, and critical audit vulnerabilities. This paper introduces Financial Safety for Teens Pay (FST Pay) as an architectural and formal specification. FST Pay is founded on an immutable operational boundary: strict deterministic safety gating on the real-time authorization path coupled with decoupled downstream AI explanation. Transactions initiated via rails like UPI are subjected to six deterministic invariant checks covering spending limits, guardian co-sign policies, transaction amount thresholds, merchant category codes, temporal access intervals, and hardware integrity constraints. Transactions are classified strictly into ALLOW, REVIEW, or BLOCK outcomes through an ordered, mutually exclusive decision function. High-risk transactions trigger an asynchronous guardian co-sign workflow. Generative AI is relegated entirely downstream of settlement, consuming published post-decision events solely to generate natural-language financial insights without holding mutation privileges over the ledger.

Replay attacks are the most accessible threat to voice-controlled systems, and the acoustic cues that expose them are strongly modulated by the environment in which the attack is mounted. A detector deployed in the field therefore has to absorb new acoustic conditions over time, ideally without revisiting past recordings, since retaining speech indefinitely is both expensive and legally constrained. We frame this as Domain-Incremental Learning (DIL) over acoustic environments and present the first continual learning benchmark for multi-channel replay speech detection, evaluating a state-of-the-art beamformer-based detector over all 24 environment orderings of the ReMASC corpus with five seeds. Sequential fine-tuning forgets severely, raising the error rate on previously learned environments by 18.8 points. Elastic weight consolidation (EWC) halves forgetting but loses plasticity, gradient projection memory (GPM) is statistically indistinguishable from naive fine-tuning, and the proposed task-specific beamformer (TSB) that keeps one spatial front-end per environment significantly improves final and incremental accuracy. We further show that the last environment of the sequence dominates final performance. Code, results, and analysis are available at https://github.com/michaelneri/replay-speech-continual.

The open web ran on an unwritten bargain: sites admitted crawlers, and search engines sent visitors back. Public measurements show that bargain breaking under AI crawlers and agents. Automated clients now make up most requests, training dominates Cloudflare-classified crawling, and the largest AI platforms fetch thousands of pages for each visitor they return. The web's common control, robots.txt, cannot express identity, purpose, terms, or price, can be circumvented, and newer alternatives are largely proprietary CDN features. We specify terms.txt, a robots.txt-style file for per-path, per-purpose machine-access terms, plus an origin-enforced exchange using Web Bot Auth signatures, signed intent, delegation tokens, HTTP 402 negotiation, and signed receipts. We define what the exchange can enforce, audit, and leave to contract. A dependency-free implementation adds 0.20 to 0.65 ms per request on one vCPU.

In February 2024 the U.S. Federal Communications Commission (FCC) placed AI-generated voices under the Telephone Consumer Protection Act (TCPA). Yet no peer-reviewed measurement says how much unwanted call traffic is placed by a machine, or how much of that machine speech is synthesized rather than played from a recording. We report both with a disclosed pipeline. An interactive voice honeypot (language-model personas on real U.S. numbers, the caller recorded on its own track) recorded 10,987 calls over 66 days. Three instruments read each opening: an audio fingerprint that finds the same recording played on other calls, a commercial synthetic-speech detector on the caller's first ten seconds, and blinded listeners who check what it flags. Of the 7,233 greeted calls we analyze, 13.8% open with a recording we also heard on another call, and 13.1% with fresh audio the detector labels synthetic. A further 9.9% open with a caller who never spoke after our greeting, 54.2% with fresh audio the detector labels human, and 9.0% could not be scored. Machine-voiced openings are therefore at least 26.9%, a further tenth of calls are silent connections we read as machine-placed, and replays of a recording make up 45% of the detector's own rate (29.3% of 6,192 scored openings). The same waveform played on two calls lands on opposite sides of the detector's threshold 13.6% of the time, and eleven listeners confirm 54.4% of what it flags. Synthetic openings concentrate in lead-generation spam (33.8%), not fraud (21.1%); 0.44% disclose automation. Prevalence tracks how long a bait number has circulated (59% against 19% in the same weeks): seeding history, not calendar time, explains the trend. Campaigns outlast their numbers: one recorded compliance notice opens calls in six campaigns, and one synthetic voice serves nine.

Retrieval-Augmented Generation (RAG) can ground large language model (LLM) outputs in external evidence, but it also exposes the system to knowledge poisoning. Representative attacks use multiple injected documents or templates that directly assert a target answer. We present ToxicRAG, a one-document-per-target attack that expresses misinformation as a coherent knowledge-update narrative. The generated document first acknowledges the previously accepted answer, introduces fabricated events that appear to invalidate it, and then attributes the attacker-selected answer to a set of purported authorities. An answer-focused self-validation loop optionally revises a candidate when a surrogate language model does not reproduce the target answer. We evaluate the attack on 100 target questions from each of Natural Questions, HotpotQA, and MS-MARCO, using four victim LLMs and four dense retrievers. In the sampled-corpus setting reported in this paper, ToxicRAG obtains ASRs between 0.61 and 0.91 across the twelve dataset–model combinations. It matches or exceeds the strongest evaluated baseline in every combination, with margins ranging from 0 to 11 percentage points. These results show that narrative-form poisoned documents can remain influential under the evaluated RAG configurations and motivate further study of factual consistency and source provenance in RAG systems.

LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifacts, and receive rewards from outcome procedures. This interactivity makes evaluations vulnerable to reward hacking: an agent improves its measured score by exploiting the reward-relevant trajectory instead of solving the intended task. Existing defenses rely largely on task-specific patches, prompt instructions, or post-hoc detectors. They do not provide reusable evidence that a concrete run remained within its intended evaluation boundary. This paper presents BenchShield, a model-backed instrumentation layer for reward integrity in LLM-agent evaluation. BenchShield grounds detection in a finite lifecycle model of an evaluation's reward-relevant events. Within the benchmark infrastructure, two complementary analyses operate over this model. A static, phase-aware taint analysis exposes reward-hacking paths before a run. Its runtime counterpart uses infrastructure-side evidence to attribute concrete agent use and emit evidence-backed claims. We construct BenchShield Trajectories, a human-labeled corpus of 456 adjudicated trajectories from more than 31,000 public agent runs across three benchmarks. Compared with an agentic hackability scanner baseline on the same tasks and model, BenchShield improves full-chain recall from 23-94% to 77-100%, same-vector coverage from 16-56% to 43-78%, and reduces per-task cost by up to 65%. Its runtime analysis achieves 96% accuracy in detecting reward hacking from infrastructure-side evidence.

Autonomous agents increasingly perform long-horizon tasks involving tool use, persistent state, and consequential actions, raising a fundamental question: under what conditions does an agent cross the boundary of authorized execution while pursuing a legitimate task? Existing studies often attribute such failures to adversarial instructions, malicious environments, or conflicting objectives, leaving unclear how loss of control can emerge during otherwise legitimate task execution. We study this question by independently manipulating three factors: goal pressure, control degradation, and executable unsafe opportunity. Our central hypothesis is that a degraded control boundary becomes consequential when the environment exposes an executable action that crosses it, even when the underlying task remains legitimate and a sanctioned path remains feasible. We test this hypothesis in a deterministic multi-turn environment across five agent models and 16 operational domains. Across 1,800 unique trajectories, we find that neither degraded control nor unsafe opportunity alone produces substantial loss of control; when both are present, the loss-of-control rate reaches $55\%$ in the full-factorial study and $62\%$ across ten additional operational domains. Restoring the original control boundary reduces the rate to $0\%$ even when the unsafe action remains executable. A context-management ablation further shows that compaction itself is not harmful: preserving the control constraints yields $0\%$ loss of control, whereas omitting them increases the rate to $87\%$. These results show how a latent loss of control can become an external violation: the task objective remains intact, but an executable opportunity can turn a missing control boundary into consequential action. Our code will be made publicly available at https://github.com/Tencent/AI-Infra-Guard/tree/main/Research/forge_bench.

Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying smart contract logic are intricately intertwined. This autonomous interplay, while eliminating centralized intermediaries, significantly expands the vulnerability surface of DeFi protocols to Price Manipulation Attacks (PMAs), which have already inflicted catastrophic financial losses. Despite their gravity, existing detection paradigms suffer from fundamental limitations. Transaction-centric methods lack awareness of contract execution semantics, making them prone to false positives under legitimate market volatility, while static contract analyses ignore real transaction behaviors and frequently report vulnerabilities that are infeasible to exploit in practice. We present DeFiFusion, a dual-modal PMA detection framework that closes this gap by jointly modeling transaction events and smart contract semantics within a unified pipeline. Our core insight is that PMA maliciousness emerges only from the interaction between transaction behaviors and the contract logic they exploit; neither signal suffices in isolation. Accordingly, we derive price-manipulation-aware event encoding for extracting fine-grained temporal and economic features tailored to manipulation patterns. We further introduce LLM-based contract semantic extraction to supply the execution-logic context that prior behavioral methods lack. To fuse these modalities, we propose a Dual-Modal Projection-Fusion Transformer with T5-style relative positional encoding, capturing the cyclic multi-stage execution structures that distinguish PMAs from benign market activity. Extensive experiments demonstrate that DeFiFusion consistently achieves state-of-the-art detection performance, effectively recalling 222 of the 225 PMA cases while maintaining a precision of 96.10%.

The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current privacy-preserving methods typically employ context-agnostic static rules, causing severe utility degradation. However, the specific mechanisms governing how sanitization impacts downstream performance remain largely underexplored. To address this, we conduct a systematic analysis to deconstruct the privacy-utility trade-off, uncovering three underlying mechanisms: (1) Context-Dependent Utility, which first establishes when to sanitize by revealing that data value shifts from critical constraints to dispensable noise based on user intent; (2) Strategic Adaptation, which subsequently determines how to sanitize by dictating that the choice between removal and replacement depends on the task's reliance on factual integrity versus structural coherence; and (3) Combinatorial Interplay, which finally extends the protection scope by demonstrating that attributes form a semantic web of synergistic dependencies or antagonistic redundancies. Guided by these insights, we introduce an intent-driven local protection framework. By distilling a lightweight model Veilmind-4B to drive a dynamic extraction-sanitization-restoration pipeline, our approach reaches a low-leakage privacy point while preserving substantially higher response utility than existing privacy-oriented baselines, advancing the privacy-utility trade-off toward the Pareto frontier.

Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baseline classifiers: Logistic Regression, Linear SVM, and Random Forest. Clean training is compared with poisoning rates of 5%, 10%, and 20% using clean-test accuracy, macro-precision, macro-recall, macro-F1, and, for backdoors, attack success rate. Label flipping caused clear degradation, largest for Logistic Regression and Linear SVM, while Random Forest stayed comparatively stable. Backdoor poisoning reached attack success rates from 0.9667 to 1.0000 on both datasets and all three models while often keeping clean-test performance near baseline. The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.

Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model, a privacy risk that matters in natural language processing (NLP), where training data can contain sensitive user text. This paper presents a controlled benchmark of membership inference vulnerability for text classification on the GLUE SST-2 sentiment dataset. A TF-IDF + Logistic Regression pipeline and a fine-tuned DistilBERT classifier are compared under a loss-threshold MIA, with utility measured by development accuracy and macro F1. DistilBERT reached 0.9466 accuracy and 0.9460 macro F1 against 0.8756 and 0.8727 for Logistic Regression, yet both models leaked membership signal (Attack AUC 0.5615 and 0.5800, respectively). Two mitigations were tested. Stronger regularization reduced leakage for Logistic Regression at a visible utility cost, whereas fine-tuning DistilBERT for 2 epochs instead of 3 reduced leakage with negligible accuracy loss. Lightweight training adjustments can improve the privacy-utility trade-off without complex defenses.

Persistent AI agents revise beliefs, consolidate memory, and replace execution substrates. Similar successor states can accompany differently authorized transition claims, while legitimate development can change state substantially. We introduce the Cognitive Continuity Test (CCT), a policy-relative contract for verifying submitted transitions using scoped authority, provenance, deterministic application, semantic predicates, and candidate-persistence receipts. CCT distinguishes verified admissibility, affirmative violation, and unresolved required evidence. Separation results concern transition claims rather than live runtime identity; soundness is conditional on the specified checker and evaluator assumptions. IdentityLineageBench provides 24 generated transition families. The reference post-resolution verifier matches all 576 canonical held-out labels; lexical state similarity and a lineage-only diagnostic baseline admit 60.0% and 80.0% of invalid fixtures. These comparisons establish synthetic conformance, not superiority to a policy-aware deployed system. Signed adversarial regressions cover fabricated interaction counts, unsupported belief changes, and mixed missing/contradictory evidence. SIT behavior and actual model migration remain unmeasured. An 18,000-execution valid-path study measures a 6.21 ms default median on resident inputs. We specify the additional activation and recovery obligations needed for deployment.

Agent developers increasingly compare prompts, tools, policies, and diagnosis algorithms through simulator-grounded verifiers. A verifier can nevertheless make a solver comparison vacuous: if its probes or predicates encode the target identity, an exact optimizer may appear effective without resolving any genuine ambiguity. We report such a failure in an aggregate-trace debugger for a closed-loop decision agent. Exact minimum hitting set (MHS) and a propagation-aware greedy method returned identical supports in 12/12 development cases and the same planted-fault recovery in 9/12. A subsequent audit found that exact-anchor predicates produced the planted pair in 9/9 cases. After removing those anchors, overall planted-pair recovery was 8/9; hard-probe singleton pairs nevertheless matched the planted pair in 9/9, and no case retained a nonempty residual conflict family after propagation (0/9). The optimizer was correct, but the verifier had already disclosed the answer. We replace solver-first evaluation with a support-gated verification contract. A clean reference map must first show repeated component exposure; a matched reference/current gate must then establish comparable runtime evidence; only afterward may an independently calibrated signal rule return a detection. In a preregistered heldout comprising 1,440 cases and 21,600 partition rows, 55/72 regime-component units passed the reference gate, 54/55 passed the runtime gate, and stable false admission was 0/20 represented components with a one-sided exact 95% upper bound of 0.1391. Within admitted units, affected clean traffic predicted detection better than nominal fault-cell fraction. The main lesson is structural: verify evidence eligibility and non-revelation before optimizing the component selector. Otherwise a stronger solver can merely certify a stronger verifier artifact.

One-Pixel Attacks (OPAs) represent one of the most extreme demonstrations of adversarial fragility in deep learning, where modifying a single pixel can reliably induce high-confidence misclassification across domains such as medical diagnosis, autonomous driving, biometrics, and quantum communication. Despite their conceptual simplicity, OPAs remain underexamined in existing adversarial-attack surveys, which provide only fragmented or cursory coverage. This PRISMA-guided review synthesizes high-quality studies from 2017 to 2026 and delivers a unified, multi-axis taxonomy of OPA research spanning algorithmic foundations, black-box evolutionary optimization, emerging hybrid and program-synthesis attacks, defence mechanisms, interpretability tools, and domain-specific vulnerabilities. Our analysis reveals the dominance of Differential Evolution-based strategies, the rise of efficiency-optimized and saliency-guided methods, and persistent gaps in dataset diversity, transferability, and standardized evaluation. We summarized and assess defence paradigms including pixel restoration, anomaly detection, input-space transformations, and robust training highlighting their trade-offs in robustness, imperceptibility, and computational overhead. Building on these insights, we outline future research priorities involving selective pixel recovery, transformer-specific vulnerability analysis, saliency-driven optimization, and real-world domain-adaptive defences. We further propose a regulatory framework emphasizing robustness testing, incident disclosure, and AI security governance. This review establishes a comprehensive foundation for understanding, evaluating, and mitigating ultra-sparse adversarial threats in contemporary AI systems.

The possible emergence of fault-tolerant quantum computers may enable widely used cryptographic algorithms to be broken. These algorithms for public key encryption and digital signatures could be exposed if an efficient algorithm is employed. This poses a threat to existing infrastructure, motivating the development of mechanisms that can withstand quantum-computer cybersecurity risks. However, the transition to new security mechanisms is still underway and faces many challenges, including identifying which applications are under threat and implementing agile, scalable migration processes. In this work, we survey the state of the art in quantum-safe cryptographic mechanisms, existing applications targeting migration, and open challenges. We examine the building blocks commonly used to integrate quantum-safe mechanisms into existing applications and categorize them by the security mechanisms they employ. Next, we systematically review existing migrations into quantum-safe schemes and categorize them by application domain, including Telecommunications, the Internet of Things, and Blockchains. Finally, we summarize the challenges that must be addressed to enable a successful migration to quantum-resistant mechanisms, as well as the motivations for pursuing this migration.

When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls, a poisoned observation, and a suffix of actions that serve the attacker. An operator needs three facts: where the attack entered, which steps it corrupted, and whether apparent poison was resisted. Existing systems return either a whole-trace verdict or a single unsafe index. We present DriftNet, a dual-head trajectory Transformer that reads a logged tool-call trajectory and answers all three questions in one forward pass: one head classifies the trajectory as compromised or not, and a second assigns every step one of four labels (benign, injection point, hijacked, failed injection). To our knowledge it is the first supervised detector to produce this joint output. A frozen sentence encoder and four identity-free world features embed each step; the trained trunk, under two million parameters and optimized with a class-weighted joint objective over both heads, needs no access to the agent's model. On the task-disjoint split of the AgentDrift benchmark (12,536 trajectories, 71,024 labeled steps), with a 20-configuration sweep bounding hyperparameter sensitivity to 0.011 F1 and the test part evaluated exactly once, DriftNet reaches trajectory-level F1 of 0.983, exact injection-point recovery on 98.7% of attacked trajectories, hijacked-span IoU of 0.979, zero flags on 218 resisted attacks, and 2.9% flags on hard negatives. A surface baseline retrained on the identical split recovers 11.1% of partial hijacks and 17.1% of delayed executions; DriftNet reaches 98.6% and 93.2% while lowering every false-alarm rate. Reading all 26 residual errors shows that most misses trace to trajectories whose labeled injection observation carries no legible instruction, and we report the benchmark's measured world-identity regularity alongside the results.

Organisations operating in regulated and critical-infrastructure sectors must satisfy multiple, heterogeneous cybersecurity and privacy instruments simultaneously, including but not limited to ISO/IEC~27001, the NIST Cybersecurity Framework~2.0, Cyber Essentials, and the GDPR. In practice, these obligations are managed through manual mappings, spreadsheet-based tracking, and periodic audits that are costly to maintain, inconsistent across standards, and weak in traceability. This paper presents AspisAI, a bounded, standard-agnostic governance framework that translates selected requirements from several frameworks into a canonical, machine-interpretable control model, and evaluates submitted evidence against condition-based decision rules to produce explainable, traceable compliance determinations. Within a bounded scope of 26 representative requirements, the framework is evaluated in a controlled simulation against five governance-oriented criteria and, critically, against two external reference points that mitigate the circularity of single-author evaluation: its cross-standard mappings are validated against NIST's own published informative references, with 57\,% exact agreement and divergences confined to same-family controls, and the framework is applied to real third-party evidence from the OpenSSF Scorecard, surfacing genuine governance gaps in a live open-source project. The controlled results, comprising full requirement encoding, 88.5\,% mapping coverage, complete traceability, and correct detection of all introduced gaps, establish functional correctness, while the external validation provides evidence of applicability beyond the simulation. The contribution is therefore a demonstration that a canonical, provenance-preserving governance model can render multi-standard compliance both automatable and auditable.

This paper studies fundamental graph optimization problems under differential privacy (DP) and shows new, reconstruction-based lower bounds. We consider a graph $G = (V, E, \vec{w})$ where the vertex set $V$ and edges $E$ are public and the weights $\mathbf{w}:E\rightarrow \mathbb{R}$ must be kept differentially private under an $\ell_1$ neighboring relation. For the problems of releasing a minimum-weight spanning tree and a minimum-weight perfect matching, we show new, tight error bounds of $\Omega(n\cdot\log(m/n)/\epsilon)$ on worst-case graphs with $n$ vertices and $m>2n$ edges. The upper bounds are known pure DP algorithms while the new lower bound holds even under approximate $(\varepsilon,\delta)$-DP as long as $\delta \leq (n/m)^{\Omega(1)}$. Our lower bounds improve the $\Omega(n/\epsilon)$ lower bounds of Sealfon (PODS~'16). The fact that approximate DP does not reduce error for MST under the $\ell_1$ neighboring relation contrasts with the recent upper bound of Pagh et al. (PODS~'25) which shows that approximate DP allows much better error under the $\ell_\infty$ neighboring relation. Going beyond worst-case graphs, we give lower bounds for large families of sparse graphs with expansion properties. We show a lower bound of $\Omega(n / \epsilon)$ for the minimum spanning tree for any graph where the minimum cut is at least $\Omega(\log(n))$. Finally, we consider the problem of private hierarchical clustering under Dasgupta's cost function (STOC~'16) and show the first approximate DP lower bound parameterized by the minimum weight of a balanced cut. This extends lower bounds of Deng et al. (ICLR~'25) to general graphs and to approximate DP.

The Agent2Agent (A2A) protocol, now governed by the Linux Foundation, is an open standard that enables autonomous AI agents to discover, authenticate with, and delegate tasks to one another across organizational boundaries. Designed to complement the Model Context Protocol (MCP) for tool integration, A2A is rapidly emerging as the horizontal communication layer of the multi-agent ecosystem. Yet the protocol's security has received no systematic analysis. This paper presents A2ABreak, the first rigorous systematic security analysis of the A2A protocol. We introduce a novel framework that utilizes an LLM-assisted extraction of a verified finite-state machine directly from the natural-language specification, producing a unified model of 37 states and 76 transitions from 929 formalized statements, and then systematically reasons over this model to discover protocol-level vulnerabilities through adversarial verification, under a full-compliance assumption. Our analysis uncovers 11 new vulnerabilities, each exploitable by a specification-compliant adversary without requiring any implementation flaw. Among the findings are cross-client context injection through unprotected context identifiers, credential harvesting via multi-hop identity loss in delegation chains, and data exfiltration through rogue agents advertising unattested capability claims. A2ABreak achieves 73.3% precision and 84.6% F1 against manual expert review, while a zero-shot LLM baseline operating over the same specification produces zero confirmed findings, demonstrating that explicit formal grounding is essential for sound protocol security analysis.

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box vulnerability analysis in which neither access nor runtime interaction is available, and only functionality metadata is available. Such metadata defines the intended behavior of the system, including its inputs, outputs, and side effects, while constraining the space of implementations consistent with that behavior. We propose hypothesizing about vulnerabilities that exist across all possible implementations of a given system metadata, without observing or interacting with the target system. An analyst can later validate these hypotheses when additional access is available. We showcase the feasibility of no-box vulnerability analysis through implementing a prototype called MCPSEC, which audits Model Context Protocol (MCP) servers for indirect prompt injection vulnerabilities using only the tool metadata exposed at server registration time. We evaluate MCPSEC on 20 widely deployed MCP servers comprising 177 tools, among which human evaluators confirm 95 vulnerable tools. MCPSEC identified 143 tools as vulnerable, and for each vulnerable tool, it produced a hypothesized vulnerability along with exploitation technique. Using metadata alone, MCPSEC predicted 94 (98.9% recall) real verified vulnerabilities, compared against an LLM baseline with 80 (84.2% recall). Overall, our results introduce no-box vulnerability analysis as a new analysis paradigm and demonstrate its practical feasibility in realistic systems.

When a language model finds a sentence unusually cheap to predict, it is tempting to conclude that the sentence was in its training data. Almost every published test of that inference has had to guess which sentences were in the training data, the members, and which were not. This paper removes the guessing. Two model families, OLMo-2 and Pythia, publish their pretraining corpora, and a public index over those corpora returns the exact number of times any sentence appeared in each. Those counts make three questions answerable directly. The answers form a pincer, closing from two sides. At the duplication levels ordinary text actually has, five models from 1B to 13B parameters carry at most a faint trace of their own exposure. We measure that trace with a design that reads the same sentence through two models, which cancels fluency and quality by construction, and it comes to a rank correlation near -0.08, where -1 would be a perfect relation and 0 none. Where the trace does become strong, above roughly a thousand copies, the two corpora agree on which sentences those are, because they are the famous ones, so exposure can no longer be told apart from fame. Two further measurements show how apparent membership signal gets manufactured. A common way to build a non-member is to change one word of a member. The model does prefer the original, but the gap is the same, within noise, whether the original appeared once or a hundred times, so what the model is rewarding is the author's word choice, not memory. Above a thousand copies the gap grows with model size on the twelve sentences we can test there, at the same boundary where the pincer closes. And swapping the controls for sentences that differ from the members in register moves a detector from 0.83 to 0.94 AUC, on a scale where 0.5 is a coin flip and 1.0 is perfect separation. We release the sentence banks, counts, and code.

How much memory is needed to retain the quantum speedup for collision finding? For a uniformly random function $f:[N]\to [N]$, the BHT algorithm finds a collision using $O(N^{1/3})$ queries and a quantumly accessible classical table containing $O(N^{1/3})$ input-output pairs, whereas a logarithmic-space Grover search uses $O(\sqrt N)$ queries. Determining the optimal query-space tradeoff between these extremes remains a major open problem. We resolve this equation within the class of label-symmetric algorithms, which treat the function $f$'s output labels as interchangeable. We prove that such algorithm that makes $T$ queries, uses $S$ qubits, and finds a collision in a uniformly random function $f:[M]\to [N]$ with constant probability satisfies $$T=\Omega(N^{1/3}) \qquad\text{and}\qquad T^2S=\Omega(N\log N).$$ For the setting where $M=N$, these bounds are matched by a space-efficient implementation of the BHT algorithm. As a consequence of our tradeoff, any label-symmetric algorithm for the search version of Element Distinctness on $f: [n] \to [n^2]$ must satisfy $$T=\Omega(n^{2/3}) \qquad\text{and}\qquad T^2S=\Omega(n^2\log n),$$ matching Ambainis's quantum walk. Thus, both tradeoffs are optimal within the class of label-symmetric algorithms. To prove these results, we develop a space-sensitive version of the compressed oracle technique. The compressed oracle records the information learned by the algorithm in an evolving superposition of databases. Using label symmetry and representation theory, we show that an algorithm using $S$ qubits can effectively retain information about only $O(S/\log N)$ collision-free database entries. Substituting this estimate into the compressed oracle technique yields the stated tradeoffs.

Large language model (LLM) agents are increasingly applied to penetration testing, but we still know little about what they can do or how they fail. We compare two PentestGPT-based systems: a legacy human-in-the-loop system running the open-weight Kimi K2.5, and a newer autonomous system running Claude Opus 4.8. Across three public targets, the autonomous system solves all three, including the two the legacy system never finishes. The legacy result is the more surprising of the two. Even on the machines the legacy system fails to solve, it completes about half the subtasks, while running on ordinary university GPUs with no provider guardrails. We can describe the trend but not explain it, since model, harness, autonomy, and memory architecture all change together. Its direction still points to the next question: what will limit these agents as they take on more complex tasks? The usual answer is long-horizon memory, the loss of access to earlier findings during long attack chains. We test it by adding a coverage-memory layer to both systems, and neither improves outcomes. In the legacy stalled runs we could review, the limiting factor appeared to be planning and commitment rather than lost memory: agents held the evidence for a route forward and never turned it into a concrete exploitation hypothesis, which may suggest that offensive capability will advance with agents' ability to plan rather than with better memory. The same subtask scoring that tracks this capability is available to defenders, who can measure it as it rises instead of waiting to meet it in the field.

Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Static analysis is widely adopted as a scalable, reproducible, and inexpensive security gate, but cannot directly observe runtime exploit behaviour. Vulnerabilities dependent on adversarial inputs, execution context, or exploit chaining may evade static checks while remaining exploitable in practice, yet passing static analysis is often treated as evidence of secure behaviour. This paper introduces the Static-Pass Dynamic-Fail (SPDF) phenomenon and a three-stage agentic pipeline combining static scanning, LLM-driven Common Weakness Enumeration (CWE) reasoning, and autonomous exploit verification in isolated Docker containers. We evaluate 1,355 Python samples from SecurityEval, RedCode, and CyberNative datasets. Of the 654 samples producing no findings under the composite Bandit-Semgrep gate, the LLM detection stage identified 394 candidate vulnerabilities across 235 files. Dynamic verification confirmed or partially confirmed exploitability in 95 files, yielding an inclusive pipeline rate of 14.53% (roughly 1 in 7 statically clean samples). This rate represents the proportion of Bandit-Semgrep-clean samples for which the pipeline identified a candidate vulnerability and obtained runtime evidence supporting exploitability. Outcomes varied by dataset: among candidate file–CWE pairs, confirmed exploitability was 33.7% for RedCode, 28.6% for CyberNative, and 5.4% for SecurityEval. Several frequently confirmed classes, including CWE-338 and CWE-916, were flagged by neither Bandit nor Semgrep. These findings indicate that static-analysis success and runtime security are hierarchical layers of software assurance rather than interchangeable measures, and have the potential to reshape how AI-generated and security-sensitive code is evaluated.