Papers

Background: Iterative feedback loops are the dominant paradigm for improving LLM-generated Infrastructure-as-Code (IaC): validators such as Checkov and terraform validate feed error signals back for successive repair attempts. Prior work reports cumulative-best metrics, which are non-decreasing by construction, so the raw per-iteration security trajectory has never been examined for IaC. Aims: We study security regression (a previously-passing CIS Benchmark check that fails after a repair iteration) to determine whether and how often iterative LLM repair degrades security while fixing other issues. Method: We analyze 5,968 scenario timelines from the IaC-Eval benchmark, each one scenario run through one configuration for up to 5 repair iterations. The 15 configurations (six model-specific RAG, nine model-aggregated non-RAG, three temperatures each) yield 4,440 iteration transitions with Checkov data on both sides. We track 30 individual CIS check IDs and classify root causes from code diffs, under two detection modes: standard (inclusive) and strict (exclusive check failures only). Results: Under standard detection, 13.8% of scenarios (24.8% of transitions) exhibit at least one regression. Under strict detection the rate falls to 3.3% of scenarios (5.2% of transitions), indicating most apparent regressions are multi-resource measurement artifacts. Resource restructuring (79.0%) is the dominant root cause. Regression transitions show 2.6x more code churn (Cohen's d=0.90) and 4.9x higher strict-mode check volatility (d=1.49). Of standard-mode regressions, 36.6% self-correct within an average of 1.2 iterations; iteration 3 is the optimal stopping point. Conclusions: Iterative IaC repair does introduce security regressions, but the conservative, defensible rate is about 3.3% of scenarios. Our findings motivate security-aware feedback-loop design and actionable iteration-budget guidance.

Telegram Mini Apps are Web applications embedded within the Telegram client, forming an ecosystem of third-party services within one of the world's most widely used messaging platforms. Despite their growing adoption and access to Telegram-provided context, their privacy properties remain largely unexplored. Unlike ecosystems such as WeChat, which rely on tightly controlled, proprietary execution frameworks, Telegram adopts a different model: Mini Apps run inside a WebView, combining platform-provided context with standard Web capabilities and unrestricted outbound networking. This enables applications to transmit sensitive information to analytics, advertising, tracking, or other third parties through ordinary Web requests, often with limited visibility. Privacy disclosures are therefore critical for transparency. Telegram allows Mini Apps either to define an application-specific privacy policy or to rely on a platform-provided default policy. While the latter reduces the developer's disclosure burden, it may lead to generic statements that do not accurately capture actual data practices of individual Mini Apps. In this paper, we present TeleGapper, a black-box dynamic analysis framework to assess the privacy posture of Mini Apps by capturing runtime network traffic, identifying third-party communications, and comparing observed data flows against disclosed privacy information. We evaluate 278 working Mini Apps collected from tApps Center, a community-driven catalogue for discovering third-party applications in Telegram. We find that 59.4% contact at least one undisclosed third party, 78.8% rely exclusively on Telegram's default privacy policy, and none provides a consent or opt-out mechanism. These findings expose a substantial transparency and compliance gap in a widely used yet understudied ecosystem.

Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, inter-zone paths, and access-control policies. Existing NetOps automation tools mainly operate after this design is fixed, providing limited support for generating structured security topologies from underspecified natural-language requirements. We present TopoIntent, a system that compiles security intent into executable, compliance-checked network topologies. It uses a schema contract to constrain generation, retrieves reference architectures from a curated template library via dense-vector search, and applies staged fusion for intent-template alignment and security completion. The generated topology is checked against CIS Controls v8.1.2 safeguards visible at the topology layer, while unresolved cases are marked for manual review. Structural gaps are repaired through additive schema-preserving edits. The final topology is exported to Mininet scripts with kernel-level iptables ACLs, enabling executable reachability and allow/deny tests. Because no public benchmark exists for this requirement-to-topology task, we construct an evaluation set from reference security architecture diagrams. The retrieval set contains 22 templates and 44 synthetic intents across five scenarios, while the held-out set contains 7 templates and 14 intents from finance and government scenarios excluded from retrieval. On the held-out set, additive repair improves topology-visible CIS satisfaction from 0.78 to 1.00 in fewer than 1.5 rounds on average, and one feedback round raises the post-ACL policy pass rate from 0.78 to 0.88.

Repackaging of mobile applications (aka app cloning) not only threatens the security and privacy of mobile users but also infringes upon the copyright of the original app developers. However, existing detection methods that primarily focus on mobile platforms (such as Android) fail to capture the essential features of virtual reality (VR). Consequently, they are inadequate for effectively detecting cloned VR apps, which have often been targeted by illegal users in the VR market. Considering the unique features of VR apps, this paper proposes a two-stage app clone detection framework, namely VR-Themis, based on Hierarchy-Object-Behaviour (HOB). Firstly, VR-Themis exploits the coarse-grained stage to cluster apps based on their retrievable statistical features, making this tool scalable to large-scale VR app datasets. Then, in the fine-grained stage, VR-Themis performs in-depth analysis of the suspicious apps (identified in the first stage) by calculating similarity using our defined HOB metrics. Our extensive experiments indicate that VR-Themis successfully detects 307 suspected clone apps from the collected 4,277 VR apps without false positives, demonstrating its effectiveness and scalability.

A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political will to decide which other countries may use these systems. In June 2026 the United States required a leading developer to obtain licences before releasing its most advanced models to any foreign person, including foreign nationals resident in the United States. The affected models were withdrawn worldwide at short notice, partly because the restriction proved impractical to administer. This followed within months of the first documented case of a largely autonomous, AI-run cyber espionage campaign, and coincided with mounting evidence that frontier models alter the economics of both cyber attack and cyber defence. This article examines how these two developments interact, and situates them within the unusual market dynamics now driving large-scale AI development. It argues that access to frontier AI is becoming part of national cyber defence, that such access can be revoked, and that the obvious remedy of sovereign capability remains only partly feasible for all but a handful of states. Drawing on evidence about training costs, the concentration of computing power and the support offered by national AI programmes, it asks what sovereignty can realistically mean for small and middle powers, and for large powers as well. The article proposes a layered strategy: negotiated access guarantees, sovereignty at the level of inference, hedging with open-weight models, pooled regional capability, sustained talent development and continued investment in basic cyber resilience. The open-weight hedge proves at once more capable and more politically exposed than is commonly assumed. Much of the near-term risk lies in how capable models are deployed and contained rather than in their apparent performance.

Our work presents a defense mechanism against Maximal Extractable Value (MEV) opportunities in distributed ledgers. The mechanism relies on the idea of enforcing a verifiable delay when generating transactions, such that a block creator cannot react to the appearance of a MEV opportunity without breaking liveness. We present positive results both in the Byzantine setting and in a game theoretic model of rational participants. We additionally present negative bounds that outline the limitations of this line of defense. Finally, we explore real-world implementation details of verifiable delays and show that, based on historical MEV data, our mechanism could realistically help prevent most existing MEV threats.

Aggregating logical information in continuous-variable quantum networks is essential for distributed quantum architecture. However, direct passive linear optics degrade non-Gaussian Gottesman-Kitaev-Preskill (GKP) grid states via symplectic lattice compression and entanglement-induced decoherence when auxiliary modes are discarded. We present an active, measurement-based continuous-variable network primitive for combining spatially distributed computational-basis payloads. Utilizing GKP Bell states, homodyne measurements, and conditional feed-forward phase-space displacements, we construct a completely positive trace-preserving (CPTP) map that evaluates a logical XOR operation on computational-basis inputs. We bound the Heisenberg action of the physical finite-squeezing channel on logical Pauli generators, demonstrate measurement-specific homodyne-outcome hiding for continuous-variable quantum one-time pads (CV-OTP) with an explicit prefactor bound $D_{\mathrm{TV}} \le 1.60 e^{-r}$, and evaluate logical success probabilities under physical optical loss and network scaling constraints.

Blockchains are among the most adversarial environments in computing. Billions are stolen by cybercriminals who exploit vulnerabilities. This is an open problem and no concept or technique has proven to really make a difference. In this paper, we claim that the classical notion of program invariant is perhaps the most powerful solution to the problem. We devise anoriginal experimental protocol to 1) study how invariants would have protected against past real-world attacks and 2) whether state-of-the-art automated tools can find them. The experimental toolchain is sophisticated. It is based on INVARIANTEVAL, a benchmark of 28 real Ethereum exploits, each paired with a human-authored invariant that blocks the attack. We validate every invariant with PONDEREPLAY, a replay framework that re-executes transactions in order to prove the correctness and soundness of smart contract invariants. We demonstrate that smart contract invariants block all the cybercriminal attacks in INVARIANTEVAL, fully validated by replaying 108,637 historical transactions. Our large-scale experiments clearly demonstrate that smart contract invariants protect against cybercriminals.

Cloud storage clients increasingly require authentication that remains secure against future quantum-capable adversaries, motivating hybrid constructions that combine classical primitives with standardized post-quantum alternatives. Extended naively to multi-file upload, such constructions incur a per-file lattice signing cost that dominates authentication time and becomes prohibitive at realistic batch sizes. This paper presents a commitment-based hybrid post-quantum model that addresses this bottleneck. It comprises AES-256-GCM bulk encryption, a hybrid X25519 with ML-KEM-768 key encapsulation mechanism, and a hybrid Ed25519 with ML-DSA-65 dual signature, computed over a SHA3-256 batch commitment. The commitment binds all ciphertexts in a batch to a single fixed-size digest that is signed once, reducing the number of post-quantum signature invocations per batch from n to one, independent of batch size; the remaining encryption and hashing is bounded by fast symmetric throughput. On a commodity client platform, averaged over 20 repetitions, this holds signing-phase time near-constant as the batch grows while the per-file baseline scales linearly. At n = 1000, the model reduces signing-phase time by factors of 629, 606, and 725 for 100 KB, 1 MB, and 10 MB files respectively, against a per-file dual-signing baseline sharing every other primitive.

When a security researcher publishes a report on a cyberattack, detection engineers are supposed to turn it into working detection rules. In practice, most automated attempts at this only extract the simplest clues from the report — bad IP addresses, domain names, and file hashes — and turn them into block lists. This is a weak strategy, because attackers can change these simple clues within hours or days, so the resulting detections stop working almost as soon as they are deployed. Security teams describe this idea with the Pyramid of Pain. This project asks whether feeding a report into a knowledge-graph retrieval system, Microsoft GraphRAG, rather than a standard vector-similarity retrieval system (Naive RAG), produces detection plans that rely more on these durable, top-of-pyramid clues. Both systems are given the same report, the same generation instructions, and the same language model to write the final plan; only the retrieval step differs. In a detailed case study of one APT28 report, the GraphRAG plan kept firing at 100% of its detections after every IP address, domain, and file hash in the report was rotated, while the Naive RAG plan kept firing at only 29%. Repeating the comparison across nine real CTI reports from four vendors confirms the same pattern: GraphRAG plans consistently reach higher, harder-to-evade levels of the pyramid, even when the two systems end up close on total score. The results support treating knowledge-graph-aware retrieval as the architecturally correct foundation for automatically generating SOC-deployable hunting plans, while showing that the wording of the generation prompt matters almost as much as the retrieval back-end itself.

Processor specifications underpin critical security and program- analysis tools such as disassemblers, decompilers, and emulators, yet, their correctness is rarely examined. Errors in specifications distort program behaviour, obscure vulnerabilities, and enable analysis-evasion techniques. Validating processor specifications is a non-trivial task. Our study is a significant undertaking to enable, for the first time, the systematic validation of open-source SLEIGH language specifications, predominantly used by Ghidra. We design and implement a testing framework based on an automated oracle validation strategy by proxy. Our approach leverages the structure encoded in a specification itself to enumerate decodable instruction forms and generate targeted initial states. Then differentially test the successful decoding and emulation of those instructions by comparing emulators exercising the processor specification against hardware references. Applying InSPECtor across diverse, open-source specifications—x86-64, AArch64, ARM/Thumb, RISC-V, MSP430—embedding differences in specification styles, author preferences, and instruction set architecture designs, we uncovered over 38,920 discrepancies that led to 125 unique bugs with proposed fixes, identifying decoding and semantic defects as well as cross-vendor inconsistencies. We distill our findings into 8 concrete recommendations to drive future improvements. Our work underscores the importance of specification correctness and provides a practical tool to substantially improve the fidelity of SLEIGH processor specifications, strengthening the reliability of downstream security and analysis tools.

The emerging Internet of Agents enables LLM-powered agents to discover peers, invoke tools, and delegate tasks across organizational boundaries. Existing protocols increasingly define how agents exchange messages, but not how an agent proves its identity, authorization, advertised capabilities, or accountability after delegation. We present InterSAGE, a trust-native protocol suite that supplies this missing security substrate alongside, rather than in place of, communication protocols. InterSAGE comprises four layers: Persistent Identity, Discovery, Trust Negotiation, and Accountability. Its four core primitives are: (1) Agent Identity Cards that bind developer, code package, operator, and deployment context; (2) capability-aware discovery using DID-bound Verifiable Credential manifests; (3) trust negotiation combining monotonic capability attenuation with two-tier access control; and (4) kernel-mediated cryptographic audit trails that bind usage, delegation, and execution traces to agent identity without a consensus ledger. InterSAGE is designed to complement MCP, A2A, ANP, and AG-UI, allowing communication protocols to evolve independently while keeping trust semantics explicit, portable, and verifiable. We compare InterSAGE with more than 50 efforts spanning agent protocols, decentralized identity, OAuth/OIDC extensions, zero-trust governance, delegation, and audit architectures. We show that no prior architecture jointly enforces persistent identity, capability-aware discovery, trust negotiation, and accountability as a unified four-layer trust substrate for secure agent interoperability.

Retrieval-augmented generation uses an external corpus as inference-time evidence, allowing an attacker to promote a false answer by injecting a handful of documents. Detection must distinguish this manipulation from ordinary relevance without knowing which queries or documents are targeted. Existing detectors use text irregularity, candidate consensus, or corpus-level graph structure, whose reliability varies with the attack and local context. We present RAGSieve, which constructs a reference matched to each detection scope. At query time, RAGSieve-Query (RSQ) compares generation candidates with the lower-ranked tail of the same retrieval, exposing answer-token concentration and carrier-payload seams. At corpus time, RAGSieve-Graph (RSG) compares each document's strongest semantic relations with its own neighborhood floor to measure coordinated density. Neither requires poison labels, a trusted corpus, or training. Across three QA datasets, three dense retrievers, and six poisoning constructions, RSQ reaches 95.2% AUROC and detects 82.2% of poison at a 5% clean-removal budget, against 81.1% and 52.5% for the strongest query-time baseline; RSG reaches 93.3% and 79.8% against 79.4% and 37.6% for the strongest corpus-time baseline, with a 79.6% versus 1.4% detection rate on camouflaged injections. Joint deployment cuts attack success from 67.4% to 16.1% while retaining unpoisoned-retrieval F1 at 41.0%, compared with 42.1% without filtering. Source code is available at https://github.com/XrazyMee/RAGSieve.

Mix networks are an important tool to implement anonymous communication, which protects not just the content but also the metadata of messages. Over time, various packet formats for mix networks have been proposed, usually with single, specific goals in mind. These formats are incompatible with each other, requiring separate software and infrastructure to be set up. In this paper, we propose a new format, OmniSphinx, which solves this issue. In OmniSphinx, senders embed code in their packets that determines how they must be processed. The resulting active mix network can emulate any other mix format within a single deployment. Our empirical evaluation shows that emulation in OmniSphinx incurs reasonable overhead compared to native execution for typical mix network use cases: For Sphinx, the most compact format, computation time increases by around 90{\mu}s, while headers increase by 33% in size.

Autonomous penetration-testing agents rely on target responses. These responses guide both subsequent actions and the final report. A deceptive response can therefore redirect both the attack trajectory and the agent's verification process. However, final reports reveal little about how an agent interprets conflicting evidence, changes course, decides to stop, or turns observations into a vulnerability claim. We introduce ATOBench, an evaluation framework that makes this verification process observable. ATOBench injects registered response transformations at runtime and pairs each transformed episode with a native episode under the same environment. Each pair is aligned at the first affected response. A source-linked reconstruction then follows later actions, evidence recovery, stopping, and report support. Three frozen observation contracts cover exploit proof, resource ownership, and reusable artifacts. We evaluate five model routes over 450 episodes. The analysis shows that increased activity can mask a broken verification chain, while successful recovery depends on finding usable evidence and preserving it through reporting. ATOBench turns deceptive target observations into a reproducible probe of evidence handling in autonomous penetration testing. This process-level view extends offensive pentest agent evaluation beyond final outcomes by revealing how untrusted observations shape actions, verification, and reporting.

The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first develop a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective. Building on this formulation, we propose HARD (Harness-based Autonomous Runtime Defense Evolution), a self-evolving runtime defense framework that automatically identifies appropriate intervention strategies and iteratively improves defense artifacts based on observed failure traces. HARD transforms runtime defense development from manual engineering into an autonomous evolution process, and extensive experiments demonstrate that it improves security performance over existing handcrafted defenses while preserving benign task utility. Our findings highlight autonomous defense evolution as a promising new paradigm for securing deployed LLM agents, enabling agents to identify defense weaknesses and continuously improve their protection mechanisms.

Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withhold information about the learning task, while other contributors participate without exposing their local datasets, creating an asymmetric information structure aligned with growing privacy demands. However, this asymmetry is a double-edged sword. Among various threats, backdoor attacks are particularly concerning because VFL not only enables malicious contributors to poison the model during training, but also allows them to activate the backdoor at inference time to manipulate predictions. Although prior work has reported near-perfect attack success rates and proposed effective defenses, we find that most findings fail to hold under realistic conditions, exposing a fundamental gap between research and practice. In this paper, we present a systematic, practice-oriented study of backdoor vulnerabilities in VFL, revealing this gap in both methodological design and evaluation practices. We show that existing approaches overlook key practical constraints and therefore rely on unrealistic prior knowledge. Furthermore, these limitations have remained hidden due to poorly designed evaluation practices in the literature. To bridge this gap, we redefine threat models under realistic constraints, propose practical backdoor workflows, and introduce BVBench, a backdoor-centric benchmark that enables fair, practical, and comprehensive evaluation, preloaded with state-of-the-art baselines. BVBench provides strong evidence of the fragility of the current understanding of VFL backdoor risks and establishes a foundation for steering research toward uncovering practical vulnerabilities and developing more meaningful defenses.

This IEEE PES Task Force report examines the security and resilience of large-scale Energy Internet (EI) systems, in which electricity, information, and market layers are tightly coupled through pervasive digitalization. The report characterizes the EI cyber-physical threat landscape and surveys detection, assurance, and mitigation techniques, presents modeling, control, and decision-making frameworks that capture cyber-physical interdependencies, including storage integration, multi-dimensional resilience, and electricity price forecasting, examines adversarial risks and trustworthy deployment of artificial intelligence, and introduces graph-based, attack-resilient information routing. The report closes with recommendations for research, standardization, and regulatory efforts needed to realize a resilient and secure large-scale EI.

While the privacy risks of multimodal large language models (MLLMs) have drawn significant attention, the unique vulnerabilities of domain-specific MLLMs remain largely underexplored. Focusing on document understanding MLLMs for identity document processing, this paper investigates the privacy issues inherent in Key Information Extraction (KIE) tasks. We reveal that when input images lack sufficient visual evidence, these models often rely on memorized field relations from training data to infer missing content, thereby leaking multiple correlated fields containing sensitive personal information. To mitigate this risk, we make three key contributions.First, we propose the Dynamic Relational Unlearning Framework (DRUF) which comprises a Relational Decoupling Unlearning (RDU) module and a dynamic set update mechanism. It suppresses the leakage of high-risk field pairs while preserving KIE performance.Second, we introduce DocPrivacyBench, a novel benchmark to systematically evaluate a model's susceptibility to privacy leakage under conditions of absent or minimal visual evidence.Third, we evaluate three MLLMs and six unlearning methods using this benchmark, assessing both post-unlearning leakage suppression and utility preservation.Our results demonstrate that existing MLLMs consistently exhibit privacy leakage when visual evidence is scarce, particularly on noisier datasets. In contrast, DRUF outperforms the strongest baseline by improving leakage suppression by 4.8 percentage points, effectively mitigating privacy risks while maintaining robust document information extraction performance.

Smishing detection systems are commonly trained and evaluated on clean, monolingual text. In low-resource settings, however, attackers frequently circumvent these systems through character obfuscation, cross-lingual code-switching, and structural perturbation. This study evaluates adversarial robustness for five model architectures: three classical lexical models (Random Forest, XGBoost, CNN+BiLSTM) and two multilingual transformers (mBERT, XLM-RoBERTa), using a dataset of 27,037 messages. Classical models are subjected to black-box generic attacks, while transformers are evaluated with attention-guided targeting. Each model is tested across three attack types and intensity levels, with performance measured by the Robustness Degradation Ratio (RDR). The results reveal a distinct architectural boundary: classical models experience near-catastrophic failure under character obfuscation and structural perturbation (RDR up to 0.988), whereas transformers demonstrate significantly greater resilience (RDR up to 0.351), with structural perturbation representing their most pronounced vulnerability. Effect-size analysis (Cliff's d) indicates a substantial difference between the two model categories. Within the transformer group, XLM-RoBERTa, despite achieving a higher clean-text baseline, exhibits greater degradation than mBERT. These findings demonstrate that clean-text performance is not a reliable predictor of adversarial robustness. Statistical validation using Mann-Whitney U and Friedman tests confirms that these patterns are attributable to model architecture rather than sampling. The results underscore the necessity for architecture-specific defences and frame smishing detection as an adversarial cybersecurity challenge rather than a static classification task.

Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external payload-family corpus was not. The historical grader exhibited direct treatment leakage: treatment metadata gated the ATTACK_SUCCESS class, so fixed behavior could change class under treatment relabeling. A treatment-blind reconstruction corrects 58 historical ATTACK_SUCCESS or HIJACK_ATTEMPT labels to authorized benign completions while preserving three verified protected-data transfers and one separate unauthorized-forwarding case. The locked v2 census contains exactly zero ATTACK_SUCCESS records, while the forwarding case remains a HIJACK_ATTEMPT at a semantic boundary concerning objective completion. A dual-reviewer blinded concordance review of all 96 requests deemed structurally interpretable by locked v2 produced identical reviewer-consensus classes but differed from the locked codebook on four construct-boundary cases. We contribute a seven-link Integrity Chain and an executable, scope-bounded endpoint-integrity linter. The result is a campaign-bounded measurement audit, not a population attack-rate, model-ranking, defense-efficacy, or causal estimate.

Public blockchain data enables large-scale DeFi-related analysis, but many existing approaches are application-specific, difficult to scale, or hard to interpret. This research proposes a scalable, application-agnostic framework for persistent behavioural pattern discovery from large-scale blockchain activity. It constructs behaviour sentences enriched with contract, token and market context, then applies a two-step embedding process: sentence-level embeddings capture individual actions, while sequence-level embeddings capture user behaviour over time. An interpretable behavioural profiler characterizes discovered communities through behavioural motifs, routines, temporal dynamics, entity exposure, and suspiciousness evidence. Evaluation on Ethereum using over 30 million transactions shows that the framework uncovers both routine and malicious behavioural patterns, including decentralised exchange (DEX) trading, NFT activity, phishing, bot operations, oracle manipulation, and rug-pull schemes. Importantly, many patterns remain stable across independent observation windows, enabling the identification of long-term behaviours beyond a single analysis period. The proposed framework combines scalability, interpretability, and persistence analysis, supporting blockchain forensic investigation, behavioural attribution, and threat discovery.

Many software systems expose multiple execution modes through command-line options, subcommands, and configuration flags. For such programs, fuzzing depends on both mutated inputs and the invoked mode. Yet evaluations still focus on coverage and bug counts, leaving unclear how execution modes partition, overlap, and miss software structure, and how these differences affect effectiveness. We present an empirical study of software structure under multi-driver fuzzing. We propose a structural abstraction that uses a static call graph as a shared backbone and projects driver-specific dynamic coverage onto it to derive driver-induced subgraphs. Based on this abstraction, we develop a four-phase methodology for backbone construction, fuzzing and profiling, graph-based analysis, and research-question-driven evaluation. We apply it to 27 OSS-Fuzz-derived C/C++ projects, spanning 43 executables and 854 driver configurations. Under the same total budget, multi-driver fuzzing outperforms the best single-driver baseline, increasing covered call-graph nodes by 27.9% and CFG-edge coverage by 73.5%, and revealing 11 unique bugs and abnormal behaviors largely missed by single-driver fuzzing. However, driver contributions are uneven, subgraphs differ substantially in cohesion, fragmentation, modularity, overlap, and residual under-exploration follows recurring regimes rather than a homogeneous tail. These results show that multi-driver fuzzing is fundamentally a structural exploration problem.

Python package security is largely source-centric, yet Python runtimes can execute bytecode directly through .pyc files, compiled-only modules, and marshalled code objects, creating an inspection-execution gap. We present an empirical study of Python bytecode as a security artifact. We measure bytecode exposure in PyPI distributions, evaluate practical analyzability using version-aware tooling, assess CPython runtime robustness under adversarial bytecode, and test source-level reproduction of bytecode findings. Across 1,034,843 collected PyPI artifacts, we identify 7,388 bytecode-containing artifacts, including 228,578 .pyc files and 28,193 artifact-local source-less .pyc files. For modern CPython 3.8-3.14 bytecode, at least one selected decompiler emits source for 204,901 of 204,904 in-scope files, a result measuring emission rather than verified functional equivalence. Tools are non-robust: observed PyPI bytecode triggers managed-code exceptions and timeouts, while adversarial mutated bytecode also drives decompilers into native process failures; together these outcomes yield 17 distinct robustness signatures. Fuzzing produces 1,009 stack-deduplicated runtime findings dominated by pointer-dereference symptoms; 261 groups exhibit potential memory-corruption characteristics, and at least 91.7% of groups reach execution beyond the documented-unsafe ingestion boundary. None reproduce from ordinary Python source. Bytecode is thus a visible ecosystem artifact, a practical analysis target, and a security-relevant interpreter input whose behavior need not match source-level behavior.

Confidential VMs (CVMs) have become the dominant substrate for sensitive cloud workloads, from financial services to privacy-preserving AI inference. The hardware isolation that protects these CVMs from a malicious cloud also blinds their owners to what runs inside them: kernel rootkits planted via network or supply-chain attacks can hide processes, tamper with kernel data, and exfiltrate model weights under the cover of the same isolation that defends the VM. Tenants therefore need to inspect a running CVM from outside, yet classical VM introspection (VMI) presupposes a trusted Hypervisor, which CVMs exclude from the TCB. The state-of-the-art CVM-VMI system, 00SEVen, restores introspection on AMD SEV-SNP via an in-VM agent at a privileged tier (VMPL0), a mechanism that does not exist on Arm CCA, leaving Realm VMs without any introspection solution. We present RealmEye, the first VMI system for Arm CCA Realm VMs. RealmEye places the entire introspection logic inside the Realm Management Monitor (RMM) at R-EL2, achieving hardware-enforced separation between the monitor and the monitored VM: no agent runs inside the Realm, and the Realm remains unmodified. RealmEye reads Realm memory and registers, suspends the VM for consistent snapshots, and traps page-level accesses, without relying on any in-VM interface. A periodic, self-driven trigger mode keeps scan timing internal to the RMM, preventing the Hypervisor from colluding with in-Realm rootkits. Results are returned to the remote owner over a hardware-attested channel, and a CCA driver backend lets existing tools such as LibVMI and DRAKVUF interoperate with RealmEye unchanged. On the Arm FVP, RealmEye detects process hiding and syscall-table hooking by Diamorphine, and its in-RMM cost is linearly predictable from primitive invocation counts.

Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey. We show that this gap enables state-corruption attacks, in which attacker-controlled content makes environmental claims beyond the informational authority of its response component and corrupts the agent's perceived environment, making the resulting action appear justified to existing guardrails. We introduce PIPES (Provenance-Informed, Prior-Enforced Screening), which screens response units using semantic priors and source provenance. PIPES uses static field contracts when schemas provide stable expectations, and conditions screening of open-ended content on the pre-response trajectory and trusted provenance metadata. It marks units that violate their semantic prior or the provenance hierarchy; deployments may remove, warn, block, or escalate detected violations. We instantiate atomic removal and evaluate PIPES against adaptive PAIR-style attacks. Across the three VitaBench and three AgentDyn splits with Gemma 4 31B IT as the target agent, PIPES reduces average attack success from 84.7% to 2.3%, while preserving average benign utility (92.5% with PIPES versus 90.6% without defense).

Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the wrong authority, an unsupported completion claim, or work made stale by a later change. We define governed execution as work whose decisions, completion, and response to change are supported by inspectable provenance. We present Matrix, a deterministic causal-state layer that records authority and fact dependencies, verifies completion evidence, and selectively invalidates affected work. Across controlled comparisons, governed and direct workflows often reached the same outcomes, but only the governed path consistently preserved governing evidence, refused unsupported closure, and limited recovery to dependent tasks. A role-separated transfer challenge then failed: a deterministically enforced completeness contract severely over-blocked synthetic packets produced outside its authoring context. These results do not establish Matrix as a general accuracy enhancer; they support its primary role as an institutional integrity layer for making agentic work auditable and independently verifiable.

Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness allows an adversary to alter critical content while retaining attribution, a vulnerability known as piggyback spoofing. We introduce an innovative watermark that jointly provides provenance and tamper evidence. It co-embeds a robust signal and a fragile signal into each generated token. The signals share the same mechanism but use independent keys and different seeding windows over normalized text, making one resilient to edits and the other sensitive to reader-visible changes. Multiple rounds of unbiased tournament reweighting preserve the expected generation distribution, while a periodic round-allocation pattern controls the trade-off between the two signals. At detection, their scores form a two-dimensional space supporting three decisions: Intact, Tampered, and No-Watermark. Across two large language models and two prompt datasets, our method demonstrates the highest tamper-detection rate among the evaluated methods while maintaining competitive attribution robustness and perplexity. Ablation studies show that reliable three-state detection requires a well-defined notion of intactness, co-embedding of the two signals, and complementary sensitivity to edits.

Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing privacy research on RAG has focused on preventing unauthorized users from accessing sensitive data. However, another important problem that is often overlooked in RAG privacy research is that external generators have access to the query and the retrieved documents, which may contain confidential information that could potentially be misused or accessed for unintended purposes. In this paper, we introduce the Sensitive Entity Alias Generator (SEAG), a privacy-preserving framework that empowers users to utilize powerful third-party generators without disclosing sensitive information. SEAG introduces a lightweight model that locates sensitive entities, generates corresponding aliases, and constructs an entity replacement table. The table is used to replace sensitive words in the user's query and in the retrieved documents before they are forwarded to an external generator. For this purpose, two datasets were constructed: one for fine-tuning SEAG models to generate entity replacement tables, and another for evaluating the entire SEAG framework. The experimental results demonstrate the success of the SEAG framework. As for the User metric, which measures the ability of the model to provide a correct response to the user while hiding sensitive information from the external generator, all SEAG models achieved over 80% accuracy. Additional analysis further evaluated the ability of SEAG models Qwen-3, LLaMA-3.2, and Phi-4 to hide all sensitive entities within given documents. The results show good performance with total accuracies of 77.83%, 76.73%, and 74.91%, respectively.

Deep code models (DCMs) are increasingly embedded in code intelligence tasks. However, their robustness under adversarial attacks remains insufficiently understood. Prior black-box attacks mainly rely on identifier- only substitutions or structural edits transferred from reference samples, yielding perturbation spaces defined largely independently of the attacked input. We introduce Strike, an input-conditioned black-box adversarial robustness-testing framework that constructs and searches a hierarchical perturbation space for each input. Strike first partitions code into blocks and uses an LLM to generate context-specific structural candidates, filtered for syntactic validity, ranked by similarity, and adaptively combined. It then refines the best structural variant through similarity-guided identifier substitutions drawn from dynamically constructed candidate pools. Evaluations across representative code intelligence tasks, including clone detection, vulnerability detection, and code summarization, demonstrate that Strike achieves higher attack success rates with competitive target- model query overhead. Strategy-specific static checks across all three tasks and execution-based validation on the executable Juliet vulnerability-detection subset provide complementary, task-bounded evidence regarding the validity of the generated variants. Representation similarity and human evaluation further indicate that the variants remain highly similar to the original code and contextually natural. Fine-tuning with Strike- generated samples improves cross-attack performance on fixed perturbed evaluation sets while preserving clean performance.