Artificial Intelligence Detection

Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements. Existing approaches either detect deception without task integration or document attacks without proposing defenses. We formalize deception-aware web agent defense and propose DUDE (Deceptive UI Detector & Evaluator), a two-stage framework combining hybrid-reward learning with asymmetric penalties and experience summarization to distill failure patterns into transferable guidance. We introduce RUC (Real UI Clickboxes), a benchmark of 1,407 scenarios spanning four domains and deception categories. Experiments show DUDE reduces deception susceptibility by 53.8% while maintaining task performance, establishing an effective foundation for robust web agent deployment.

In multi-agent systems (MAS), a single deceptive agent can nullify all gains of an agentic AI collective and evade deployed defenses. However, existing adversarial studies on MAS target only shallow tasks and do not consider adaptive adversaries, which evolve their strategies to evade the very detectors trained to catch them. To address that gap, we introduce GAMBIT, a benchmark with three evaluation modes and two independent scores for evaluating imposter detectors: the first two modes measure zero-shot detection under increasing distribution shift, and a third recalibration mode measures how quickly a detector adapts to novel attacks from just 20 labeled examples. The benchmark comes with a dataset of 27,804 labeled instances spanning 240 co-evolved imposter strategies. Our contributions are threefold: (1) Using chess as a substrate deep reasoning problem and Gemini 3.1 Pro for agents, we release GAMBIT and its dataset to evaluate imposter detectors under realistic constraints against a stealthy adaptive imposter; (2) We introduce an adaptive imposter agent based on an efficient evolutionary framework, generalizable beyond chess, that collapses collective task performance while remaining essentially undetectable (50.5% F1-score with a Gemini-based detector); (3) We show that zero-shot evaluation can be highly misleading for adaptive adversaries: two detectors with near-identical zero-shot scores differ by 8x on few-shot adaptation, while the meta-learned variant converges 20x faster, a gap only visible in the recalibration mode. Altogether, GAMBIT provides the first multi-agent benchmark where adversarial attacks and defenses co-evolve, with an imposter framework generalizable beyond our use case, and promising techniques for fast recalibration in a rapidly evolving adversarial system. Code and data: https://anonymous.4open.science/r/gambit.

Insider threat detection assumes that an adaptive insider leaves behavioral residue distinguishing them from legitimate users. We test this assumption against an LLM-driven adaptive insider in a controlled multi-agent simulator. Our pre-registered five-condition study isolates defender mode (cascade vs. blind UEBA) crossed with adversary type (naive vs. adaptive OPSEC) plus a no-mole control, across 100 runs (95 valid after pre-committed exclusions). The primary finding is a detection inversion: at T_60, the adaptive mole's suspicion in-degree is statistically lower than a randomly selected innocent agent (Cliff's delta = -0.694, 95% BCa CI [-0.855, -0.519], Mann-Whitney p << 0.01). The pre-registered prediction was the opposite direction. A pre-registered equivalence test (H2) shows adaptive OPSEC produces no detectable shift in the mole's UEBA rank under either defender mode. The two detection signals (peer suspicion graph in-degree and per-agent UEBA rank) decouple under adaptive adversary behavior. We bound generalization explicitly: a pre-registered Gini calibration check (H4) returns FAIL, with HBEE pairwise message-exposure Gini (0.213) diverging from the SNAP Enron reference (0.730) by |Delta Gini| = 0.52, exceeding the equivalence bound by 5x. The paper makes a narrow but surprising claim: in a controlled environment where adaptive OPSEC is implementable as an LLM directive, peer-suspicion-cascade detection inverts. We release the simulator, pre-registration document, frozen scenarios, raw telemetry, and analysis pipeline under an open-source license.

Modern cybersecurity relies heavily on static machine-learning-based malware classifiers. However, transformations such as packing and other non-semantic modifications applied to executable files limit their reliability. Malware classifiers often learn these unnecessary artifacts rather than the true binary behavior because of the high association between maliciousness and packing. Moreover, these malware classifiers are black boxes, making it difficult to understand what they learn. To address this issue, we proposed a two-part framework using the post-hoc interpretability XAI tool TRUSTEE, followed by a manual analysis of the top features. We conducted several controlled experiments by varying the dataset composition ratios to understand their impact on the results. The top-ranked features across all experiments, identified by TRUSTEE, were predominantly packing artifacts, portable executable(PE) metadata, and n-grams at the string level, rather than malicious semantics. These results suggest that these malware classifiers are highly sensitive to dataset composition and can misinterpret packing as malicious behavior. Our proposed framework allows for the reproducible diagnosis of such biases and forms a guideline for building more robust and semantically meaningful malware detection models

Artificial satellites and space debris increasingly contaminate astronomical images, affecting scientific surveys and producing large volumes of streaked exposures. Manual inspection is no longer feasible at scale, and reliable detection and characterisation of streaks has become essential for both data-quality control and the monitoring of objects in Earth orbit. We present StreakMind, an automated pipeline designed to detect Near-Earth Objects and satellite streaks in astronomical images, characterise their geometry, and cross-identify them with known orbital objects. The system integrates all inference results into a structured database suitable for large surveys. A YOLO OBB model was trained on a hybrid dataset of 2335 images and applied to processed FITS frames. Geometric refinement, inter-frame association, satellite cross-identification, and Gaussian-based confidence scoring were then used to produce final identifications stored in a relational database. Observations from La Sagra Observatory were used to develop and test the method. On the test set, the model achieved a precision of 94 percent and a recall of 97 percent. It reliably detected faint streaks, delivered consistent geometric reconstructions, and performed robust satellite cross-identification. StreakMind demonstrates strong potential for large-scale automated analysis of linear streaks produced by both Near-Earth Objects and artificial satellites, contributing to space situational awareness.

Background: Sensitivity of AI-assisted lung nodule detection systems is known to vary with CT acquisition parameters including radiation dose, reconstruction kernel, and slice thickness. However, the dependence of detection probability on nodule position within the reconstruction cycle -- the z-phase -- has not, to the author's knowledge, been characterized for deep learning-based detection systems. Methods: A retrospective analysis was performed using the LIDC-IDRI dataset. Detection results from a previously validated 154-case perturbation study were re-analyzed. For each consensus nodule (>=4-reader agreement), z-phase was defined as the fractional position of the nodule center within the reconstruction cycle, folded to [0, 0.5]. Detection sensitivity was stratified by z-phase bin, reconstruction interval (1mm, 3mm, 5mm), and by the ratio of reconstruction interval to nodule diameter (d/D). Results: At 5mm reconstruction interval, sensitivity was 71.6% vs 84.8% at 1mm baseline. Within the 5mm condition, sensitivity varied by 17.6 percentage points across z-phase bins. Stratified by d/D ratio, sensitivity was 92.4% for d/D < 0.5, 78.0% for 0.5 <= d/D < 1.0, and 61.4% for d/D >= 1.0, with a systematic z-phase effect present only in the d/D >= 1.0 stratum. Conclusions: AI detection sensitivity depends on the ratio of reconstruction interval to nodule diameter. When this ratio approaches or exceeds 1.0 -- as occurs for 3-6mm nodules at 5mm reconstruction -- z-phase becomes the dominant source of per-study detection variance. This stochastic effect is invisible to protocol-level quality metrics and not reflected in AI confidence scores.

The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation. However, existing methods rely heavily on high-volume annotated data, which leads to substantial training costs and limited generalization. To address these challenges, we propose PrismAgent, a zero-shot, multi-agent, interpretable framework. PrismAgent conceptualizes this task as a criminal case investigation, employing four specialized agents responsible for the analysis, investigation, prosecution, and judgment stages within a structured collaborative workflow. In the first stage, the analyst agent paraphrases each meme under benevolent and malicious assumptions to probe its underlying intent. The investigator agent then retrieves supporting evidence from an unannotated dataset and constructs contextual interpretations for the meme and its variants. Next, the prosecutor agent performs three independent preliminary judgments by pairing the original meme with each of the three interpretations. Finally, the judge agent deliberates across all evidence to render a final verdict. Moreover, PrismAgent's explicit multi-stage reasoning chain makes the model inherently interpretable, as every intermediate step is explicitly explained rather than only producing a final detection result. Extensive experiments on three public datasets show that PrismAgent significantly outperforms existing zero-shot detection methods.

Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually time-consuming. In this paper, we present an experimental, agentic workflow that leverages large language models (LLMs) augmented with predefined queries and constrained tool access (structured SQL over Suricata logs and grep-based text search) to automate the first stages of alert investigation. The proposed workflow integrates queries to provide an overview of the available data, and LLM components that selects which queries to use based on the overview results, extracts raw evidence from the query results, and delivers a final verdict of the alert. Our results demonstrate that the LLM-powered workflow can investigate log sources, plan an investigation, and produce a final verdict that has a significantly higher accuracy than a verdict produced by the same LLM without the proposed workflow. By recognizing the inherent limitations of directly applying LLMs to high-volume and unstructured data, we propose combining existing investigation practices of real-world analysts with a structured approach to leverage LLMs as virtual security analysts, thereby assisting and reducing the manual workload.

Privacy-critical domains require phishing detection systems that satisfy contradictory constraints: near-zero false positives to prevent workflow disruption, transparent explanations for non-expert staff, strict regulatory compliance prohibiting sensitive data exposure to external APIs, and robustness against AI-generated attacks. Existing rule-based systems are brittle to novel campaigns, while LLM-based detectors violate privacy regulations through unredacted data transmission. We introduce CyberCane, a neuro-symbolic framework integrating deterministic symbolic analysis with privacy-preserving retrieval-augmented generation (RAG). Our dual-phase pipeline applies lightweight symbolic rules to email metadata, then escalates borderline cases to semantic classification via RAG with automated sensitive data redaction and retrieval from a phishing-only corpus. We further introduce PhishOnt, an OWL ontology enabling verifiable attack classification through formal reasoning chains. Evaluation on DataPhish2025 (12.3k emails; mixed human/LLM) and Nazario/SpamAssassin demonstrates a 78.6-point recall gain over symbolic-only detection on AI-generated threats, with precision exceeding 98% and FPR as low as 0.16%. Healthcare deployment projects a 542x ROI; tunable operating points support diverse risk tolerances, with open-source implementation at https://github.com/sbhakim/Cybercane.

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make three contributions to cross-session threat detection. (1) Dataset. CSTM-Bench is 26 executable attack taxonomies classified by kill-chain stage and cross-session operation (accumulate, compose, launder, inject_on_reader), each bound to one of seven identity anchors that ground-truth "violation" as a policy predicate, plus matched Benign-pristine and Benign-hard confounders. Released on Hugging Face as intrinsec-ai/cstm-bench with two 54-scenario splits: dilution (compositional) and cross_session (12 isolation-invisible scenarios produced by a closed-loop rewriter that softens surface phrasing while preserving cross-session artefacts). (2) Measurement. Framing cross-session detection as an information bottleneck to a downstream correlator LLM, we find that a session-bound judge and a Full-Log Correlator concatenating every prompt into one long-context call both lose roughly half their attack recall moving from dilution to cross_session, well inside any frontier context window. Scope: 54 scenarios per shard, one correlator family (Anthropic Claude), no prompt optimisation; we release it to motivate larger, multi-provider datasets. (3) Algorithm and metric. A bounded-memory Coreset Memory Reader retaining highest-signal fragments at $K=50$ is the only reader whose recall survives both shards. Because ranker reshuffles break KV-cache prefix reuse, we promote $\mathrm{CSR\_prefix}$ (ordered prefix stability, LLM-free) to a first-class metric and fuse it with detection into $\mathrm{CSTM} = 0.7 F_1(\mathrm{CSDA@action}, \mathrm{precision}) + 0.3 \mathrm{CSR\_prefix}$, benchmarking rankers on a single Pareto of recall versus serving stability.

Modern machine learning methods have been proposed to detect life in extraterrestrial samples, drawing on their ability to distinguish biotic from abiotic samples based on training models using natural and synthetic organic molecular mixtures. Here we show using Artificial Life that such methods are easily fooled into detecting life with near 100% confidence even if the analyzed sample is not capable of life. This is due to modern machine learning methods' propensity to be easily fooled by out-of-distribution samples. Because extra-terrestrial samples are very likely out of the distribution provided by terrestrial biotic and abiotic samples, using AI methods for life detection is likely to yield significant false positives.

Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupled with project-specific business logic. We observe that recurring vulnerabilities across diverse DeFi business models often share the same underlying economic mechanisms, which we term DeFi semantics, and that capturing these shared abstractions can enable more systematic auditing. Building on this insight, we propose Knowdit, a knowledge-driven, agentic workflow for smart contract vulnerability detection. Knowdit first constructs an auditing knowledge graph from historical human audit reports, linking fine-grained DeFi semantics with recurring vulnerability patterns. Given a new project, a multi-agent pipeline leverages this knowledge through an iterative loop of specification generation, Proof-of-Concept (PoC) synthesis, PoC execution, and finding reflection, driven by a shared repository index. We evaluate Knowdit on 11 recent Code4rena projects with 84 ground-truth vulnerabilities. Knowdit detects all 21 high-severity and 90% of medium-severity vulnerabilities without false positives, fully covering eight projects, significantly outperforming all baselines. Applied to seven real-world projects, Knowdit further discovers 9 high- and 36 medium-severity previously unknown vulnerabilities, securing millions in liquidity and proving its outstanding performance.

Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such misaligned actions may arise from external attacks (e.g., indirect prompt injection) or from internal limitations (e.g., erroneous reasoning). They not only expose CUAs to safety risks, but also degrade task efficiency and reliability. This work makes the first effort to define and study misaligned action detection in CUAs, with comprehensive coverage of both externally induced and internally arising misaligned actions. We further identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels. Moreover, we propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback. DeAction outperforms all existing baselines across offline and online evaluations with moderate latency overhead: (1) On MisActBench, it outperforms baselines by over 15% absolute in F1 score; (2) In online evaluation, it reduces attack success rate by over 90% under adversarial settings while preserving or even improving task success rate in benign environments.

Agent safety benchmarks measure whether a monitor detects harm, not when. Yet timing is the difference between intervention and autopsy. We introduce StepShield, the first benchmark that treats detection timeliness as a first-class metric. On 9,429 incident-grounded code-agent trajectories, we define the Early Intervention Rate (EIR): the fraction of detected rogue trajectories where the alert fires within a k-step window after the divergence point, isolating timing quality from coverage. This metric exposes what we call the Forensics Trap: a pattern-based guardrail with 847 rules achieves 86% recall yet is statistically indistinguishable from random timing on EIR (0.23 vs. 0.24; p = 0.66, one-sided binomial; difference within CI), because over three-quarters of its alerts trigger on benign prefix code before any violation occurs. The 4x EIR gap between rule-based and semantic detectors is completely invisible to accuracy, recall, or F1. Our finding is structural: regex guardrails detect syntax, not intent, and therefore cannot distinguish the moment an agent turns rogue, rendering the entire deployed class of pattern-based monitors unsuited for real-time oversight. No existing method simultaneously achieves high recall, low false-positive rate, and timely intervention, establishing step-level rogue detection as genuinely unsolved.

LLMs expand accessibility and provide wide-reaching access to information. Yet these interactions also create opportunities to embed subtle, goal-oriented behaviours that shape what users think and how they behave, a concern reflected in governance frameworks that prohibit manipulative AI. We refer to these behaviours as hidden intentions: covert agendas embedded in a model's outputs that can manipulate users' beliefs and actions. In this work, we examine whether hidden intentions can be identified and characterised, and assess whether detection can serve as a mitigation strategy. To operationalise this, we introduce a social-science-grounded set of ten hidden intention categories and show that they are trivially inducible. A case study further confirms that all ten categories manifest in deployed LLMs. We then evaluate static classifiers and LLM judges on these categories, providing the first systematic analysis of why hidden intentions are difficult to detect. Our stress tests show that, unless false-positive rates are vanishingly small, auditing is dominated by precision-prevalence trade-offs. Capability scaling and reasoning models do not close this gap, suggesting a fundamental challenge for open-world detection. These findings expose a core gap of current AI governance: without new auditing paradigms for open-world, low-prevalence risks, bans on manipulative AI remain difficult to enforce.

This paper presents a hybrid insider threat detection framework for enterprise environments, integrating multi-agent simulation, layered SIEM correlation, trust-adaptive thresholds, behavioral and communication forensics, and Theory-of-Mind reasoning. Email is treated not as a control channel but as a coordination and social-engineering evidence stream correlated with authentication, file-access, and privilege events. Four variants are evaluated: Layered SIEM-Core (LSC), Cognitive-Enriched SIEM (CE-SIEM), Evidence-Gated SIEM (EG-SIEM), and EG-SIEM-Enron with Enron-calibrated email forensics. Across ten matched runs with eight malicious insiders, actor-level F1 improves from 0.567 for LSC to 0.774 for CE-SIEM, 0.898 for EG-SIEM, and 0.944 for EG-SIEM-Enron; paired Wilcoxon tests confirm the first three differences after Holm-Bonferroni correction. Evidence gating reduces confirmed false positives from 33.7 per run under LSC and 49.3 under CE-SIEM to 0.2 and 0.0 respectively, a precision gain traded against longer confirmation time. Domain-shift evaluation shows that an Enron-trained email classifier does not transfer to a different operational email domain, although target-domain fine-tuning reaches F1 = 0.974 under grouped template-family evaluation. On CERT r4.2, the evidence-gated logic improves actor-level detection while reducing false positives, outperforming tabular anomaly detectors and a sentence-embedding baseline. Scalability tests to 1000 agents indicate stable detection quality.

Liquids like water, wine and medicine are everywhere. However, limited attention has been given to the task of segmenting liquids, hindering the ability of robots to safely avoid and interact with them. The segmentation of liquids is difficult because liquids come in diverse appearances and shapes; moreover, they can be both transparent or reflective, taking on arbitrary objects and scenes from their background and surroundings. To take on this challenge, we construct a liquid dataset, LQDS, consisting of 5000 real-world images annotated into 14 distinct classes, and design a novel liquid detection model, LQDM, which leverages cross-attention between a dedicated boundary branch and the main segmentation branch to enhance mask predictions. Extensive experiments demonstrate the effectiveness of LQDM on the testing set of LQDS, outperforming state-of-the-art methods to establish a strong baseline for the semantic segmentation of liquids. We believe that LQDS and LQDM will facilitate future research in liquid segmentation and enable practical applications in robotics. Our dataset and code is released at https://lonaslee.github.io/LQDM/.

Machine Learning (ML) malware detectors rely heavily on crowd-sourced AntiVirus (AV) labels, with platforms like VirusTotal serving as trusted sources of malware annotations. But what if attackers could manipulate these labels to classify benign software as malicious? We introduce label spoofing attacks, a new threat that contaminates crowd-sourced datasets by embedding minimal and undetectable malicious patterns into benign samples. These patterns coerce AV engines into misclassifying legitimate files as harmful, enabling poisoning attacks against ML-based malware classifiers trained on those data. We demonstrate this scenario by developing AndroVenom, a methodology for polluting realistic data sources and launching subsequent poisoning attacks against ML malware detectors. Experiments show that not only are state-of-the-art feature extractors unable to filter such injections, but various ML models experience Denial-of-Service (DoS) with as little as 1% poisoned samples. Additionally, attackers can flip decisions for specific unaltered benign samples by modifying only 0.015% of the training data, threatening their reputation and market share, while evading anomaly detectors operating on the training data. We conclude by raising concerns about the trustworthiness of ML training processes based on AV annotations and argue that further investigation is needed to develop more reliable labeling strategies.

Traditional honeypots share an invariant behavioral profile: a skilled adversary can confirm the presence of a deception environment within a few diagnostic commands, limiting their intelligence value. Commercial deception products (USD 100,000-150,000/year) similarly lack real-time model-driven feedback. Chameleon, an openly distributed adaptive honeypot, addresses both shortcomings. It integrates: a BiLSTM classifier achieving 99.61% accuracy across seven threat categories at ~2 ms CPU latency; a locally deployed Qwen3.5-0.8B model delivering 90% generation accuracy at 4.5 ms latency; and two meta-heuristic engines. Threat-Calibrated PSO (TC-PSO) reshapes swarm inertia and objective amplification in proportion to the classifier's anomaly output, adjusting connection-holding delays in real time. Semantic Deception RRT (S-RRT) evolves deception schemas via exponentially scaled pheromone updates from a language-model severity assessment, with a depth-decay multiplier enforcing a finite memory footprint. A controlled 30-seed benchmark (42-71, identical trajectories and budgets) shows threat-calibrated inertia alone does not improve search over standard PSO on static or dynamic landscapes (p = 0.18); population-diversity mechanisms (GA/ACO) significantly outperform PSO-family optimizers on threat-regime shifts (p < 0.0001, d <= -37). S-RRT's depth-decay delivers a significant memory reduction versus standard RRT (53.1 vs. 119.2 units, p < 0.0001, d = -10.0); its severity-weighted pheromone does not improve raw fitness. Operating cost is ~USD 17/month, a ~490-fold reduction versus commercial alternatives.