CyberSec Research

Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace state make the unsafe action appear useful. This makes pre-install vetting insufficient and calls for runtime, task-conditioned protection. We propose Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill. Our guard, SkillSonar, runs alongside untrusted task skills and checks sensitive actions against the user's task boundary, routing each action to an allow, replan, or confirmation decision without modifying the underlying agent runtime. To study this setting, we construct SCOPE-R, a task-conditioned dataset covering 6 risk families and 21 sub-categories, with 206 attack-confirmed malicious instances and 43 benign tasks. We then improve SkillSonar on the SCOPE-R training subset using runtime guard-skill evolution, a Monte-Carlo Tree Search procedure that evolves the on-disk guard skill from feedback on the rollouts. Across Claude Code and OpenClaw, the evolved guard substantially reduces attack success while maintaining a favorable safety-utility trade-off. On repeated GLM-5 runs, SkillSonar reduces ID ASR from 0.482 to 0.104 and OOD ASR from 0.606 to 0.115. Further analyses demonstrate transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers. Ablations further show that explicit safety responsibility assignment and the skill-native representation are both important to the observed gains.

Let $q$ range over primes congruent to $3$ modulo $4$. Let $ζ_q$ be a primitive $q$th root of unity, and put $K=\mathbb{Q}(ζ_q)$, with ring of integers $\mathcal{O}_K=\mathbb{Z}[ζ_q]$. We prove that the decision version of the Shortest Vector Problem ($\mathrm{SVP}$) in the $\ell_2$-norm is $\mathrm{NP}$-complete on full-rank free submodules of $\mathcal{O}_K^2$ by a deterministic polynomial-time many-one reduction from Exact Cover by 3-Sets (X3C). The module rank is fixed at two. As a $\mathbb{Z}$-lattice, the module has rank $2(q-1)$, which grows with $q$. The main obstacle is closure under the action of $\mathcal{O}_K$. A module containing a nonzero vector also contains every scalar multiple of that vector by a nonzero element of $\mathcal{O}_K$, and some of these multiples may be shorter. Three ideas overcome this obstacle. First, we map the Bennett--Peikert Reed--Solomon lattice to a principal cyclotomic ideal and use Wan's point-count estimates to prove that a coset of this ideal contains many binary coefficient representatives. Second, a checker based on a quadratic Gauss sum turns the X3C equations into a canonical squared norm. Third, the checker and a second module coordinate combine with a separation bound for ideal cosets to rule out every unintended vector created by the $\mathcal{O}_K$-action. Each constructed instance consists of a prime $q\equiv3\pmod4$, two integral generators whose $2\times2$ generator matrix has nonzero determinant, and an integer squared threshold. The construction also gives $\mathrm{NP}$-hardness of search-$\mathrm{SVP}$ under polynomial-time Turing reductions.

Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior work often attributes this failure to gradient conflict, we propose a fundamentally different Fisher-geometric explanation: safety Fisher is low-rank, and alignment makes the safety geometry flatter while preserving an output-routing pathway. After 100 benign fine-tuning examples, this pathway is selectively re-sharpened in output-side MLP modules, explaining the asymmetric fragility: safety can collapse to high attack success rates, while general utility degrades mildly. The routing view also explains why few safety examples can restore refusal behavior, indicating that internal safety-relevant representations are preserved. Finally, we show that LoRA and ASAM mitigate early collapse by suppressing output-side sharpness, but their protection weakens at larger fine-tuning scales. Overall, safety failure is best understood as a disruption of a low-rank output-routing mechanism

We give a sampling problem that is solvable by shallow quantum circuits, hard for polynomial-time classical algorithms under lattice-based assumptions, and efficiently verifiable by a classical computer. The quantum sampler admits two implementations: one uses log-logarithmic-depth quantum circuits with one- and two-qubit gates, i.e., $\mathsf{QNC}^0[\log\log]$ circuits, while the other uses constant-depth quantum circuits with unbounded fan-in gates, i.e., $\mathsf{QAC}^0$ circuits. Our construction can be seen as compiling the Learning with Errors (LWE)-based single-round proof of quantumness of Arabadjieva et al. (2025) to very low depth. The price paid for this compilation is the reliance on less standard, though well-motivated, assumptions: in addition to the lattice knowledge assumption used by Arabadjieva et al. (2025), we require a strengthened variant of the adaptive-hardcore-bit property of LWE, for which we provide supporting evidence. Unlike previous low-depth proofs of quantumness, the quantum computation here requires no mid-circuit measurements or feed-forward: it consists only of running a shallow circuit and sampling from its output distribution. This shows that shallow quantum circuits have sufficient structure to solve certain classically hard tasks whose solutions can be verified efficiently.

Inference cascades cut cost by answering most queries with a cheap model and escalating a hard tail to a frontier model that acts as verifier. A natural extension closes the loop: fine-tune the cheap student on the verifier's rejections so the escalation rate, and cost, fall each round. We measure this loop on real LLMs and report four findings. First, the verifier's blind spot, the fraction of the student's wrong answers it accepts, is large and moves adversarially: it grows with student capability ($β$ from 0.12 to 0.55 as the student scales 0.5B to 32B) and shrinks with verifier capability, so it is worst in the cheap-student, cheap-verifier regime cascades exist to create. Second, buying it away returns the saving: a frontier verifier drives $β$ to about 0.05 but then escalates on 46% of hard-MATH queries against a 39% true error rate, paying the frontier price on nearly half of all traffic. Third, naive corrective fine-tuning on the verifier-rejected tail does not improve the small student but degrades and ultimately collapses it, across every teacher we tried (cross-family and same-family), so at this scale the self-improving loop is self-defeating. Fourth, through all of this the cascade's own dashboard, every metric computed through the verifier, reads a flat 3% error while true delivered error swings up to 32%: the system is blind to its own degradation by construction. We then give the theory that explains the blindness, a two-population conservation law, $ε_\infty \lesssim q_0 β_0$, under which every in-loop metric improves while true quality does not, and a synthetic study that validates the mechanism. The practical conclusion: the reliability of a self-improving cascade cannot be read from any metric computed through its own verifier.

Mix networks (mixnets) provide network-level privacy by routing each communication packet through a sequence of intermediaries, called mixnodes, that randomly delay and cryptographically transform packets before forwarding them, making it difficult for observers to link mixnet entries to exits. While this mechanism protects sender privacy from both external adversaries and the receiver, existing mixnets lack a secure and practical protocol that simultaneously protects receiver (destination) privacy, particularly from the sender. We close this gap. We introduce the first practical and secure hidden-service protocol for mixnets, providing receiver privacy alongside sender anonymity. Our design builds on Single-Use Reply Blocks (SURBs), which enable anonymous replies without revealing the receiver's address. We show, however, that existing approaches to using SURBs expose two practical attacks that can compromise sender or receiver anonymity when the opposing party controls only a single mixnode. We develop defenses against both vulnerabilities. Building on these defenses, we introduce NymHS, a secure and practical hidden-service protocol for mixnets that supports anonymous service discovery, authenticated bidirectional sessions, and asynchronous SURB replenishment. We implement NymHS on the open-source Nym codebase and evaluate its practicality through web-browsing experiments across 118 websites, measuring each of the 27 configurations three times (9,558 page loads). Our results demonstrate that hidden services can be deployed efficiently over mixnets. In particular, increasing the Sphinx payload from 2 KiB to 10 KiB reduces mean page-load latency by approximately 5.2x and decreases communication overhead from 21.7% to 4.3% relative to the current Nym baseline.

Synthetic data has become a common component of machine learning research. While widely adopted, its use in privacy-sensitive contexts has quietly shifted from a claim of residual inference risk under stated assumptions to an appearance-based property inferred from data generation itself. In this position paper, we argue that this shift reflects an implicit change in community standards for what counts as sufficient privacy evidence, rather than a misunderstanding of well-established privacy principles. Drawing on an empirical analysis of recent publications across major ML venues, we show that synthetic data is frequently used in privacy-sensitive settings without explicit articulation of threat models, inference risks, or falsifiable privacy claims. As a result, privacy assurance often remains implicit, difficult to verify, and unevenly distributed, with heightened exposure for rare and minority records. We argue for treating privacy as an explicit, evidence-based scientific claim and recommend that ML venues adopt norms requiring privacy-relevant assertions to be clearly scoped, testable, and contestable.

Invisible watermarks are typically evaluated against predefined perturbations such as compression, blur, noise, cropping, and denoising. Public foundation image models expose a distinct threat: an attacker can submit a watermarked image with a single reconstruction prompt and obtain a visually faithful output from which the invisible watermark can no longer be decoded reliably. We formalize this failure mode as watermark laundering and evaluate it using a joint payload-fidelity profile that combines bit error rate (BER) with visual and semantic preservation. Across six OpenAI and Google image editing models, three representative watermarking schemes, and 1,800 reconstructed outputs, we identify two complementary laundering regimes: OpenAI models produce the strongest payload disruption across the evaluated schemes, whereas Nano Banana 2 shows that DwtDct remains vulnerable under high-fidelity reconstruction. Prompt ablations show that no single removal-oriented instruction is necessary for payload disruption, indicating that the effect is primarily induced by the reconstruction pathway rather than by explicit attack wording. Comparisons with conventional attacks further show that prompt-conditioned reconstruction constitutes a distinct operational attack interface. These findings motivate foundation-model reconstruction as a missing robustness condition in invisible watermark evaluation.

MutMem V1 introduced retention-preserving, cryptographically authorized mutation for persistent agent memory but did not provide a complete portable verification contract or clean-install reproduction path. MutMem V2 closes that publication gap without introducing a second memory engine. It specifies exact canonical bytes, domain-separated object and bundle commitments, mandatory recall-evidence membership and ordering, external trust anchors, identity epochs, revocation, authorization, request receipts, ordered disclosure, and three mutation terminal types. The released protocol contains 18 versioned object schemas, 39 recall vectors, 15 mutation vectors, and 37 closed recall failure reasons. Independent Node and Python implementations agree on verdict and primary reason for all 72 structural and cryptographic terminals; a production-conformance corpus agrees on 42/42 cases across 28 required classes. A clean Node v26.8.1 installation reaches first-boot, restart, and scheduler readiness with no experimental memories. A separately scoped 120-unit Canary experiment supports only explicit-marker traversal. Every public table regenerates from a self-hashed aggregate, and an independent verifier reconstructs the statistics and claim boundaries. Historical V1 empirical results remain historical. MutMem V2 supports claims about portable integrity, authorization, traceability, conformance, and reproducibility under stated assumptions; it does not establish semantic truth, universal robustness, or independent replication.

Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud. In this setting, token reduction lowers computation and communication costs, while token shuffling disrupts the spatial organization of the transmitted tokens, potentially limiting information leakage. However, their privacy benefits remain unclear against feature inversion attacks, which attempt to reconstruct the input from the transmitted embeddings. In this work, we show that, despite disrupting the spatial structure required by conventional reconstruction attacks, transmitted token embeddings retain substantial positional information. Based on this observation, we introduce the Spatially Aligned Reconstruction Attack (SARA), a unified pipeline that predicts token positions, restores their spatial layout, reconstructs missing embeddings using a feature-space masked autoencoder, and recovers the input image. Our results demonstrate that token shuffling provides only apparent privacy, as SARA largely reconstructs the original token organization. Token reduction offers stronger protection, but significant leakage persists when the retained tokens preserve sufficient semantic and positional information. Finally, we introduce a lightweight edge-side defense that removes positional embeddings and progressively adapts the edge-side transformer blocks through knowledge distillation. It substantially reduces attack performance against SARA, while preserving downstream task accuracy and requiring no changes to the cloud-side model.

Real-world, high-profile AI agent harnesses often rely on vendor-proprietary or opaque designs for context assembly, leaving the sources and underlying logic of assembled context poorly understood and the resulting security risks largely unexplored. In this paper, we present the first systematic analysis of context assembly designs in real-world AI agent harnesses. We study and uncover how an agent harness is designed to collect and assemble context from diverse sources, and identify a set of practical attack vectors arising from these designs. Our analysis brings to light two novel categories of attacks in the context assembly of real-world harnesses: (1) MessageRole Context Privilege Escalation (M-CPE), which occurs when attacker-controlled content originating from a low-privileged context is incorporated into a higher-privileged message role. (2) Cross-Scope Context Privilege Escalation (X-CPE), which occurs when attacker-controlled content persists beyond the context in which it was introduced. We performed a systemic security analysis of the CPE attacks against 12 real-world agent harnesses, including Claude Code and Codex. The resulting consequences include full agent compromise, remote code execution, denial of service, and manipulated tool or skill invocations, etc.

Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the response violates a policy. This distinction is critical in Chinese harmful-content evaluation, where linguistic variation and adversarial transformations can obscure risky intent. We introduce C-SafeQA, a policy-grounded benchmark for response-level Chinese safety evaluation. It comprises 538 base queries and 8,877 adversarial queries answered by four full-model LLM deployments, yielding 37,660 query-response records labeled safe, unsafe, or disputed. Reference labels are generated through agreement-aware multi-model adjudication and blind audits of stratified subsets by three safety experts. C-SafeQA supports both evaluation of target-model safety and auditing of seven automated safety judges against shared reference labels. Unsafe-response rates range from 0.93% to 3.35% on base queries and from 11.68% to 30.05% on adversarial queries. On the adversarial subset, judges show substantial trade-offs between unsafe-response recall and risk-query-conditioned safe-response false positive rate, and no judge dominates all metrics. Both acrostic transformations reduce unsafe recall for all seven judges, revealing mechanism-specific evaluator weaknesses. Dataset records, metadata, verification code, and judge scripts are publicly released to support recomputation, while benchmark construction, target-response generation, and private adjudication remain outside the release boundary.

When personal data is processed in a distributed manner by cooperating service providers, privacy risks may emerge solely from the choice of data processors included in the composition. For instance, different data processors may unknowingly rely on the same cloud provider, allowing for unintended linkability of personal data at that very provider. As such compositional risks to privacy are beyond the scope of each individual risk assessment, they are likely to be overseen when performing a data protection impact assessment. In this paper, we propose a novel protocol to detect and manage such compositional risks to privacy. Following an initial problem definition and requirements elicitation, we elaborate how our protocol identifies candidates for compositional risks and how this information may be used to improve the results of a data protection impact assessment over service compositions including multiple data processors.

Anonymity is an information flow property that provides privacy protection in the sense of non-uniqueness of system information at certain moments with respect to observations. The notion of $K$-step anonymity in the context of discrete-event systems characterizes the scenario that the state estimates cannot be a singleton within at most $K$ observational steps prior to the current instant, while infinite-step anonymity is the same as $K$-step anonymity without considering the limit on $K$. In this paper, we lucubrate $K$- and infinite-step anonymity for partially-observed discrete-event systems modeled by non-deterministic finite-state automata. First, we define two strong types and two weak types of $K$- and infinite-step anonymity that are fundamentally different from the existing notions of $K$- and infinite-step anonymity due to the consideration of strong and weak anonymous projections. Then, we develop a new methodology by exploiting the concurrent-composition technique to verify these four types of anonymity. Based on the constructed concurrent compositions, verifiable necessary and sufficient conditions for the four types of anonymity are provided, along with their complexity analysis. Finally, the upper bounds on $K$ for $K$-step strong anonymity and weak anonymity are computed.

A single vulnerability in a widely used library can cascade through millions of dependent applications, yet more than half of vulnerability database entries contain missing or incorrect affected-library information. Existing automated approaches neglect the relational structure of vulnerability databases, treating identification as an isolated text retrieval problem. In this paper, we propose Athena, the first graph-based approach for vulnerability affected library identification. Athena models vulnerability databases as a knowledge graph and reformulates the identification problem as knowledge graph completion (KGC). It comprises three key modules: a Modeling module that constructs a security knowledge graph integrating CVEs, libraries, CWE weakness types, CPE products, and software ecosystems; a Completion module that applies a modular KGC backbone to predict missing affected libraries for a given CVE via link prediction; and a Re-ranking module that retrieves KGC candidates and rescores them using a fine-tuned LLM augmented with knowledge graph embeddings, jointly leveraging structural and textual information. Our experiments on VulLib demonstrate that Athena significantly outperforms four state-of-the-art baselines, achieving a 32% improvement in Avg. F1 over the best baseline (i.e., VulLibGen). Notably, our KGC backbone with only 110M parameters already surpasses VulLibGen's best configuration at 7B parameters, demonstrating the effectiveness of graph-based modeling; the re-ranking module then provides substantial further gains, consistently outperforming the best baseline across all evaluated LLM backbones.

The Common Vulnerabilities and Exposures (CVE) database catalogs vulnerability claims in hard- and software, among them those pertaining to blockchain programs a.k.a. smart contracts. We present CVE-Smart-Contracts, a curated dataset of CVE records up to July 2026 referring to Ethereum smart contracts. The dataset contains the vulnerable artifacts (source code and runtime bytecode), labels according to three taxonomies, and function-level locations. The retrieval of CVE records, collection of additional evidence, validation of the correspondence between records and artifacts, label assignment, and vulnerability localization are automated, leaving 15% to manual analysis. The dataset does not validate the original vulnerability claims, but marks a few records obviously wrong as `refuted'. For the sake of reproducibility, all external inputs are retained, so that rerunning the pipelines results in the same outputs. The dataset comprises 491 records linked to deployed contracts, 26 referring to projects (mostly libraries), 45 without validated artifacts, and six records with refuted claims. The dataset supports empirical security research, in particular the evaluation of code analysis and repair techniques.

Reverse engineering (RE) is critical to security tasks such as malware analysis and vulnerability discovery, and large language model (LLM) agents are increasingly able to perform it autonomously. Capture-the-flag (CTF) RE challenges have become the standard proxy for measuring this capability, but evaluation rests on a single criterion: whether the agent captures the flag. This solve rate reveals neither where in the RE process an agent fails nor whether a success reflects analysis of the binary or recall of a public solution. In this paper, we propose Reveree, a diagnostic framework that scores an LLM RE agent's trajectory at three tiers: solve rate, milestone progress through an eight-stage RE schema, and a behavioral profile of its actions. Comprehension stages are scored by an outcome-blinded LLM judge validated against a human expert; all other stages are verified deterministically. Using Reveree, we evaluate nine frontier models and four prompting strategies on 88 picoCTF and NYU-CTF challenges. We find that the base model dominates performance, whereas prompting strategy is a secondary, model-dependent effect. Surprisingly, larger, newer, or costlier models are not reliably stronger. We also find that failures concentrate at the comprehension stages of the RE process, and that extra budget, persistence, or reasoning effort rescues few of them, pointing to a competence limit rather than a resource limit. Regarding memorization, while models reproduce picoCTF flags from challenge descriptions alone, NYU-CTF shows minimal measurable recall, and most solves survive surface perturbation, indicating that genuine analysis coexists with memorization. We release Reveree to the community.

Cyber Threat Intelligence (CTI) is essential for defending mission-critical infrastructure, yet the process of transforming raw attack evidence into shareable CTI remains fragmented and understudied. We conduct a literature survey of academic papers, organizing the CTI lifecycle into three stages: Threat Data Collection, CTI Generation and Sharing, and CTI Consumption. The first and third stages are well represented in the literature, whereas only a small number of papers address CTI Generation and Sharing. To learn how this stage is practiced, we survey practitioners across multiple organizations who routinely generate and share CTI. They describe a largely manual process with four recurring challenges: preventing the exposure of sensitive information, extracting indicators from noisy attack data, correlating observed behavior with standardized tactics, techniques, and procedures (TTPs), and translating CTI into the formats that sharing platforms require. Using the insights from the practitioner survey, we divide the CTI Generation and Sharing stage into four steps: Intelligence Extraction, Normalization and Enrichment, Codification, and Distribution. We then conduct pilot studies that probe the feasibility of current Large Language Models (LLMs) for each step. The pilot studies show that LLMs can assist an analyst in each of the four steps. However, the models recover only a fraction of the indicators the evidence contains, struggle to ground every claim in the supplied evidence, and do not judge what keeps shared intelligence useful to its recipients. Each step therefore requires expert supervision. Based on these observations, we derive three research directions for automating the production of shareable intelligence.