Most malware detection research focuses on identifying whether a file is malicious before it executes. Far less attention goes to what happens after infection. This paper presents an empirical analysis of post-infection malware behavior across 37 families, grounded in dynamic sandbox execution using CAPEv2. Behavioral traces are modeled as heterogeneous graphs with five node types and seven typed edge relationships, preserving relational structure that flat feature vectors discard. A voting ensemble trained on graph-derived structural features achieves 94.44% accuracy and MCC of 0.863, outperforming a flat behavioral baseline by 7.4 percentage points in MCC. A multiclass classifier distinguishes 24 malware families, and a per-family behavioral fingerprint analysis characterizes post-infection activity across registry, network, process, and API dimensions. An LLM explanation layer generates analyst-readable reports with MITRE ATT&CK mappings grounded in observed behavioral evidence. The full pipeline is deployed as HeteroScan at https://ama-andam.github.io/heteroscan.
Third-party Agent Skills extend what an autonomous agent can do, but a malicious Skill can hide data exposure or output manipulation inside a legitimate workflow. Neither reading a Skill's description nor granting it tool permissions tells whether its execution meets the user's security requirements. We introduce RuntimeTickets, a protocol that enforces and audits these requirements while a Skill runs. From released malicious-Skill datasets we derive a risk model and build adversarial-benign Skill pairs. From the task's delivery contract, a language model proposes security obligations for that task. Each obligation cites the Skill lines it answers, and the ticket tightens the host's approvals into fine-grained allowed actions but never loosens them. A runtime gate checks the recipient, object and amount of every outbound send before forwarding it, and trusted monitors record the effects within their observation scope. The ticket links these checks and observations to the approved obligations of each Skill run, and a deterministic decoder turns the ticket's status into governable data flows and verifies each obligation. Neither enforcement nor decoding involves a language model, so text injected by a Skill can change the proposal but never the rule that decides a send. We evaluate RuntimeTickets at the network egress boundary of three unmodified agent frameworks against production Skill scanners and runtime baselines, among them an AgentBound-derived allow-list and SkillGuard. RuntimeTickets eliminated both failure modes of current Skill defenses, overlook (malicious Skills let through) and overkill (benign Skills blocked): its overlook rate was 0.0% and its overkill rate 0.0%, while the scanners erred on both sides. RuntimeTickets ties approved requirements to verifiable execution evidence and offers a common foundation for the safe and auditable deployment of third-party Skills.
Respiratory sound classification from auscultation recordings is confounded by heterogeneous acquisition conditions, including recording device, auscultation site, and patient characteristics, that introduce systematic variability unrelated to the underlying pathology. Although such metadata is often available, existing approaches either ignore it or rely on na\"ive fusion strategies that do not model how distinct metadata sources influence different components of the acoustic representation. We propose a family of metadata-conditioning mechanisms for the Audio Spectrogram Transformer (AST), progressing from gated residual fusion to Feature-wise Linear Modulation (FiLM) adapted to the Transformer architecture. We further introduce two novel variants: Token-Aware FiLM (TAFiLM), which applies distinct modulation to classification and patch tokens, and Soft-Factorized FiLM (SoftFiLM), which learns soft masks to align metadata factors with disentangled feature subspaces. Experiments on the ICBHI benchmark demonstrate consistent gains across all conditioning strategies. SoftFiLM achieves 64.11% on the official 4-class task (+3.94% over the baseline) and 72.40% on the 2-class task, establishing a new state-of-the-art on the 2-class task and competitive performance on the 4-class benchmark.
Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in recent production LLMs, learned per query. In DeepSeek Sparse Attention (DSA), the attention of DeepSeek-V3.2 and the GLM-5 family, every layer is preceded by a lightning indexer that scores the whole cache and keeps the k=2048 highest-scoring tokens for the layer to attend. At long context this indexer scan, not the sparse attention it feeds, is where the decode time goes. But adjacent layers select nearly the same tokens, so a layer can attend the selection of the previous indexer layer instead of its own. This removes the dependency: each indexer then runs concurrently with the attention of its layer. The resulting Multi-layer Indexer (MLI) needs no retraining and no new weights. Its default realization changes no kernel, running inside SGLang's production decode graph; an optional fused decode kernel accelerates it further on DeepSeek-V3.2. MLI composes with IndexCache (the cross-layer reuse GLM-5.2 ships as IndexShare): IndexCache drops the indexer from some layers, and MLI hides the scan on the rest. We serve DeepSeek-V3.2 and GLM-5 under IndexCache's protocol at retentions 1/2 to 1/32 (the fraction of layers that keep an indexer) and contexts 10K to 195K. At equal retention the composition decodes faster than IndexCache: up to 14.5% faster on DeepSeek-V3.2 and 9.8% on GLM-5 at 1/2, and 7.9% and 5.1% at 1/4, largest where IndexCache keeps the most indexers and growing with context. At retention 1/r it is faster still than IndexCache at 1/(2r) while keeping twice the fresh selections: at 128K it reaches 1.32x the unmodified model's decode throughput at 1/4, above IndexCache's 1.28x at 1/8. Its LongBench, RULER and LongBench v2 accuracy stays within a few percentage points of IndexCache's.
Embodied agents are increasingly deployed in open-world environments, yet current robustness evaluations remain biased toward hazardous instructions and jailbreak vulnerabilities. A more fundamental issue is largely overlooked: agents are rarely tested under semantically sufficient but contextually minimal instructions (i.e., common in real-world human communication), where auxiliary contextual cues are absent. For the first, we identify a novel phenomenon termed Ambient Context Illusion, where agents fail to execute tasks correctly when non-essential contextual details are omitted, despite unchanged task semantics. To systematically study this, we establish VagueBench, a benchmark built upon the AI2-THOR interactive simulation environment for the evaluation of context dependency in embodied agents. We systematically consider key semantic components of instructions (entities, procedures, constraints, and prior knowledge) and derive a unified taxonomy with four categories and nine subtypes to reduce auxiliary information. VagueBench contains 1,303 instruction pairs across diverse indoor environments, constructed via a human-agent co-generation framework that integrates semantic redundancy estimation, taxonomy-guided transformation, and rigorous semantic-invariance verification. Through extensive evaluation on 6 state-of-the-art embodied agents, we observe significant degradation on VagueBench in both task performance and executability (relatively -19.65% in task success rate and relatively +54.10% in empty plan rate) revealing a strong reliance on auxiliary linguistic signals rather than core task semantics. Furthermore, we demonstrate that this phenomenon persists in real-world robotic systems, where it can lead to incorrect decisions and potential safety risks.
Diffusion models trained on distinct datasets can produce highly similar samples when prompted with the same noise input, suggesting that they learn a generalized data distribution. We investigate the role of noise injected during the sampling process, and show that it plays an important role in making or breaking this strong generalization effect. Based on this finding we investigate the robustness of sample similarity to changes in the injected noise, and find that its impact is largest in the sampling regime where broad structure already exists but the precise identity of the sample is not yet determined.
Restricting what a model can say is often mistaken for restricting an attacker's influence over its decision. An attacker can add text to the evidence and steer the model toward a wrong answer that still belongs to the allowed set. We evaluate seven decision models spanning hosted APIs, open-weight models and an encoder on 16 tasks in seven domains from Decision Bench, targeting every wrong option across 240 text examples (990 targets per model). We present Slot Attack, a black-box attack designed for decision models that appends text assembled from named components to steer predictions toward an attacker-selected incorrect option. The method relies solely on returned label probabilities, achieves success rates of 32--99\% on initially correct decisions, and identifies the effective component combinations with a median of 17--72 queries per successful attack. Accuracy and confidence do not reliably reveal this vulnerability. Models with near-identical accuracy on the sampled tasks differ by about 20\%age points in attack success. We demonstrate that an attacker can force not just one wrong answer but every available one: on about 20\% of correct decisions for the JEV models, 77\% for gpt-6-luna and 98\% for GLiNER2.5; a confidence threshold does not reliably screen the attack out. A fixed answer set constrains a decision's form, not its source; robustness must be measured per model, per task and per version rather than assumed from output format.
Language models are typically trained with a single choice of architecture on diverse domains and data sources. Modern transformers have been extensively refined for such general-purpose learning, but are they equally effective across different subsets of the pretraining data? We investigate this question by training small language models from scratch on representative subsets of pretraining data such as web text, code, and mathematics. We introduce variants of transformers in which standard activation functions are replaced with learned splines tuned on specific datasets, providing a simple way to modify their inductive biases. Using a mix-and-match of architectures and datasets, we evaluate cross-domain transfer, i.e. how well does an architecture tuned for one domain perform on data from another? We find that the tuned transformer variants improve training efficiency or generalization on all seven of our tested datasets, but the gains are often domain-specific. For example, architectures tuned on a natural language dataset such as FineWeb perform well on TinyStories, whereas those tuned on mathematics perform poorly on natural language. We identify several mechanisms underlying these improvements, including wider loss basins and more abundant "lottery tickets". Our results show that different subsets of pretraining data can benefit from different learning mechanisms, highlighting a limitation of the prevailing trend towards a small set of general-purpose architectures and optimizers. This points to an opportunity to improve data efficiency by developing domain-specific learning strategies that retain the ability to train general-purpose models.
Financial workflows need fast, calibrated, auditable decisions, not just generated text. We train System-1 decision models, small language models fine-tuned to answer typed questions (choice/score/noul) with a probability in a single forward pass, across two model families (K2-Horizon and Qwen3.5/3.8) and nine rungs from 0.8B to 32B parameters, using one frozen LoRA recipe on a public decision benchmark and two new finance corpora: a programmatic-gold policy corpus (rule-reading with exact labels) and a reality-labeled outcome corpus (19,640 realized forward-return questions in walk-forward splits, plus a sealed 2026 test of 1,360 questions). Narrow fine-tuning costs general decision competence 9-45 percentage points, a data-mixture effect that shrinks with model scale and is associated with narrow-gradient volume. On reality-labeled questions, every trained rung from 0.8B to 32B lands at the horizon-conditioned prior baseline (accuracy 0.37-0.38, no detectable conditional edge under our controls); the models respond with flat, well-calibrated probabilities that track per-horizon base rates: naturally honest uncertainty, with a mid-scale calibration sweet spot (ECE 0.026 at 2B, degrading to 0.043-0.044 at 9-32B under prior drift). A mixed-corpus remediation carries all competencies in one adapter at modest cost: it matches or slightly exceeds the generalist specialist on the public benchmark while holding the policy ceiling and near-specialist outcome calibration, yielding a deployable artifact with per-domain temperature regimes and a band-dispatch escalation analysis: sharp, dispatchable bands where rules determine answers; flat, review-routing bands where reality does not.
Large Language Models (LLMs) have shown promise for empowering search agents to tackle complex information-seeking tasks. However, since acquiring external information necessitates web search, these agents are highly susceptible to various adversarial attacks (e.g., malicious information injection or stealthy context manipulation). Existing attack strategies inevitably rely on static and human-crafted templates, failing to emulate the dynamic and complex nature of real-world threats. In this paper, we propose an adversarial self-evolution framework that integrates bi-level optimization between the attacker's strategy evolution and the defender's adaptive mitigation, to expose the vulnerabilities of search agents. Specifically, we introduce the Contrastive Rollout Evolutionary Optimization (CREO) method to drive the directional evolution of the attack strategy population via contrastive evolutionary signals. To provide a stable environment for this continuous evolution, we further construct a controlled sandbox and design fine-grained metrics to quantify internal vulnerabilities. Extensive experiments across various multi-hop QA benchmarks and frontier LLMs demonstrate that the proposed framework yields attack efficacy superior to static baselines, underscoring the urgent need to develop more robust defense frameworks.
Third-party LoRA adapters introduce serious backdoor risks: malicious adapters can maintain normal task performance while embedding hidden, trigger-activated behaviors, making them difficult to detect through standard utility evaluations. Existing removal-based defenses typically sanitize backdoored models by updating, pruning, distilling, or mixing model parameters. However, these approaches are misaligned with adapter-based deployment, where the trusted base model is expected to remain frozen. In this work, we propose LoRA-Patch, a lightweight backdoor defense tailored to LoRA adapters. Our key insight is that backdoor injection distorts the directional geometry of a poisoned adapter relative to its trusted base model. Building on this insight, LoRA-Patch suppresses trigger-activated behaviors by realigning adapter directions through layer-wise steering, without modifying the base model weights. Extensive experiments across five backdoor attacks and three models show that LoRA-Patch effectively mitigates trigger-activated backdoors, outperforming existing baselines while preserving benign task performance. Moreover, LoRA-Patch is computationally efficient, constructing patches within 20 seconds across all evaluated models and adapters. Our code is publicly available at https://github.com/FOXVEDA/LoRA-Patch.
Natural Language Processing (NLP) has been widely applied in financial domains, enabling automated analysis and retrieval of stock market information. However, traditional NLP-based systems often struggle with maintaining contextual accuracy and generating relevant responses in dynamic financial environments. To address these challenges, Retrieval-Augmented Generation (RAG) models have emerged as a powerful solution, combining retrieval-based methods with generative capabilities to enhance response quality. In this study, we present a Retrieval-Augmented Generation (RAG) system designed to generate responses related to stock market information. The system integrates retrieval-based and generative approaches to enhance the accuracy and relevance of financial text generation. To evaluate its effectiveness, we employ the ROUGE metric, specifically ROUGE-1, ROUGE-2, and ROUGE-L, to measure lexical and structural similarity between generated and reference texts. Experimental results on a dataset of 100 stock market-related queries demonstrate high ROUGE scores, indicating strong alignment with reference documents. Additionally, we assess latency to evaluate the system responsiveness, achieving an average response time of 1.16 seconds. These findings confirm that our RAG model is capable of providing accurate and timely stock market insights, making it a promising approach for financial information retrieval.
Knowledge tracing (KT) estimates learners' evolving knowledge states from interaction histories to support adaptive learning. Retrieval-augmented KT improves these estimates using cross-learner behavioral evidence, but existing approaches typically separate evidence retrieval from downstream prediction. This creates a retrieval-inference alignment gap because evidence relevance varies with the learner's evolving state and prediction context. We propose CaRe-KT, a query-adaptive framework that maintains relevance continuity between evidence acquisition and inference without equating retrieval relevance with predictive utility. CaRe-KT introduces an Evidence-Graph Cache (EGC) that combines persistent question-level relational compatibility with interaction-level temporal validity to construct query-specific evidence subgraphs. Historical learning trajectories retrieved through these subgraphs are encoded alongside the target learner's history in a shared representation space using outcome-supervised contrastive learning. An attention mechanism combines acquisition relevance with learned query-evidence compatibility, allowing relevance to inform, rather than determine, each trajectory's predictive influence. Experiments across five benchmarks show that CaRe-KT outperforms strong KT baselines and remains robust under sparse-history and cold-start conditions. These findings support relevance continuity as a design principle for retrieval-augmented knowledge tracing.
Long-term memory enables large language model (LLM) agents to provide continuous personalized assistance by retaining user information across interactions. Existing systems support this process through fact extraction, organization, updating, and retrieval, but largely maintain memories as independent facts. This fact-centric paradigm may overlook how new facts update, constrain, or conflict with earlier ones, while leaving their applicability, role, and priority for the current request implicit. In this paper, we introduce EvoMemState, a state-centric framework that augments persistent facts with two complementary states: Relational States that capture how facts remain valid and relate to one another as memory evolves, and a Reasoning State that determines how these facts should be applied to the current request. Specifically, EvoMemState consists of three key components: (i) Ontology-Guided Memory State Induction extracts Persistent Facts and constructs Relational States that maintain their validity, scope, and evolving relations. (ii) RL-Based State Evolution internalizes memory-use experience into a policy through reinforcement learning to generate a request-specific Reasoning State. (iii) State-Aware Reasoning then combines the relevant facts with their Relational States and the generated Reasoning State to guide the personal agent. Extensive experiments on long-term dialogue and memory-use benchmarks demonstrate consistent improvements over existing memory systems in retrieval completeness and memory-grounded response accuracy. Our code and implementation details are available at https://github.com/XMUDeepLIT/EvoMemState.git.
Open-set object detection (OSOD) suffers from a fundamental limitation under dense proposal mechanisms: highly overlapping proposals associated with the same object are often assigned contradictory known/unknown predictions. Existing methods perform open-set reasoning independently for each proposal, while ignoring the shared semantics among correlated proposals, resulting in fragmented detections and unstable open-set decisions. In this paper, we reformulate OSOD as an object-centric semantic inference problem, where correlated proposals jointly support a coherent region-level semantic decision. Based on this perspective, we propose OCSI-Net, a unified framework that combines object-centric semantic consistency with geometry-aware uncertainty stabilization. Specifically, OCSI-Net aggregates correlated proposals into structured region clusters and infers region-level semantics from aggregated semantic evidence, thereby enforcing coherent open-set predictions within the same object region. Furthermore, a geometry-aware uncertainty mechanism is introduced to stabilize optimization near open-set transition boundaries. Extensive experiments on multiple benchmarks demonstrate that OCSI-Net consistently achieves state-of-the-art performance, improving the harmonic mean of known and unknown detection by an average of 6.83\% over the second-best method.
We formulate and investigate the hypothesis that reasoning text has simpler co-occurrence topology than non-reasoning text, and that higher-quality reasoning has simpler co-occurrence topology than lower-quality reasoning. We discuss and test applications to AI safety and AI evaluation.
Accurate forecasting and temporal downscaling of solar irradiance is critical for reliable renewable energy integration and grid management. Traditional methods often struggle to capture rapid irradiance variability. In this work, we develop a Transformer-based architecture for simultaneous forecasting and temporal downscaling. The model takes input data at arbitrary resolutions and generates outputs at any resolutions represented within the training data, leveraging both global and local contextual information. To improve training efficiency, a genetic algorithm-based optimization framework is implemented to identify suitable model hyperparameters, while reducing the computational cost of exhaustive grid search. The effectiveness of the proposed model is shown by analyzing real data in Dallas, Texas. The proposed model achieved root mean square error (RMSE) values of 28.785, 29.544, 30.157, 32.132~W/m\(^2\) for 15-, 30-, 60-minute, and irregularly spaced global input and producing forecast at 5-minutes resolution, respectively. Furthermore, this model produced reliable uncertainty estimates, exhibiting wider prediction intervals for high-resolution inputs during volatile solar conditions, whereas coarser-resolution inputs result in narrower intervals and significantly lower training time and computational cost. Our approach provides a scalable and efficient framework for multi-resolution solar irradiance forecasting and temporal downscaling, suitable for practical energy forecasting and grid management applications.
Extracting semantically meaningful staypoints from raw trajectory streams is a foundational prerequisite for mobility analytics. However, real-world trajectory data is frequently degraded by severe spatial noise and protracted temporal dropouts. Classic threshold-based extraction methods, such as the widely adopted sliding-window algorithm, are highly sensitive to these anomalies, routinely fracturing continuous stationary episodes into disjointed fragments. To overcome this limitation, we propose the Sequential Staypoint Extraction (SSPE) algorithm. SSPE employs a resilient, state-driven architecture that replaces static spatial anchors with a dynamic centroid and introduces an $n$-step lookahead heuristic to structurally tolerate transient coordinate drift. Concurrently, it utilizes temporal bridging mechanisms to prevent artificial fragmentation during prolonged signal loss. Since optimal extraction parameters vary significantly across datasets, we further introduce a fully unsupervised, consensus-based parameter estimation framework. This framework derives baseline statistical scales directly from the raw trajectory data and identifies the optimal parameter configuration by maximizing structural agreement, thereby eliminating the reliance on annotated ground truth. We evaluate SSPE on the ExtraSensory dataset, a real-world mobility corpus with manually verified ground-truth staypoints, against the sliding-window implementation of Trackintel, one of the most widely adopted extraction baselines in the field. Empirical results demonstrate that SSPE achieves superior accuracy, yielding higher F1-scores while simultaneously improving computational efficiency over this standard.
We present HyVox, a hybrid neuromorphic--von Neumann system for low-energy open-set speaker identification under tight energy budgets. HyVox splits the workload at the speaker embedding. A neuromorphic processor embeds the speech with sparse, event-driven computation, and a von Neumann microcontroller holds the speaker gallery and makes every decision: it scores queries by cosine similarity, rejects unknown speakers, and enrolls new users by writing a prototype, with no weight update. On the neuromorphic processor, a hierarchical temporal abstraction (HTA) SNN backbone learns a synaptic time constant per leaky integrate-and-fire (LIF) neuron, allocating 832 neurons across fast, medium, and slow timescales. A 32-neuron spiking embedding extractor (SEE), pretrained on episodes that each enroll new speakers and reject outsiders, turns the backbone output into an embedding for speakers unseen in training; its 32 spike counts are the only interface between the two processors. To fit the chip's synapse and integer budgets, we compress the backbone 6.5x to 29.0k synapses, train it for integer bit-shift dynamics, and fine-tune it with chip-accurate spiking training (CAST). CAST trains through a differentiable replica of the chip's integer neuron update, derived from its cycle-accurate simulator, so that gradient descent optimizes the exact weights and thresholds the chip runs; it doubles the top-1 accuracy of the mapped backbone on unseen speakers. On 20 Common Voice households of unseen speakers, HyVox reaches 99.6\% top-1 and 5.5\% rejection EER with 2 members and 94.9\% and 13.2\% with 20, and the network deployed on the neuromorphic chip matches its trained model. Each inference on a 3-s window takes 0.96 s and 1.63 mJ of dynamic energy, 42\% lower latency than the fastest embedded ANN baseline and 13.5x less dynamic and 5.8x less total energy than the most energy-efficient one.
Training a classifier means letting a validation metric decide which model is kept and when training stops. A natural requirement on that metric is superiority: every correctly classified forecast should score better than every incorrectly classified one, however close the underlying probabilities are. Neither the Brier score nor the logarithmic score satisfies this on its own. We show that superiority is governed by the separation between two endpoints -- the supremum of the score on correct predictions and the infimum on incorrect predictions -- and derive both in closed form for each score. Their difference is the infimal penalty, the greatest lower bound on the penalty needed to restore superiority. Prior work restores superiority with a penalty calibrated from the first endpoint alone; for the Brier base, our infimal penalty is smaller than that published penalty by a factor ranging from 4.00 at three classes to 2.11 at twenty. We further embed the published and infimal penalties in a one-parameter family and show that, under a single-valued tie convention, every member of the family is strictly proper. In a pre-specified two-dataset case study, mean selected-model macro-F1 rises with the penalty in the reported ten-class regimes, though not distinguishably from noise once seed/selection-mode nesting is accounted for; a fifth regime at forty-seven classes does not reproduce even this descriptive pattern. The intended no-superiority baseline is algebraically a rescaling of the family under test, so the experiment cannot attribute the observed pattern specifically to superiority. When superiority itself is the objective, any penalty strictly above the infimal value suffices; choosing a larger penalty is a separate calibration trade-off rather than a requirement for the guarantee.