搜索结果：illegally

In this paper, we discuss question-answer dataset for LLM safety evaluation, with a focus on illegal activities. Specifically, on the basis of manual analysis of AnswerCarefully, we introduce several additional information, methods for creating question-answer examples, and a rubric for evaluating LLM-generated responses. The outcomes of this study are intended to be shared with the "JAI-Trust" project.

Illegal gold mining in the Amazon rainforest causes deforestation, water contamination, and long-term ecosystem disruption, yet remains difficult to monitor at fine spatial scales. Satellite imagery supports large-scale observation, but often misses small mining-related structures and subtle land-cover transitions, especially under frequent cloud cover. We introduce ELDOR, a large-scale UAV benchmark for monitoring environmental and landscape disturbance from illegal gold mining in the rainforest. ELDOR contains manually annotated orthomosaic imagery covering over 2,500 hectares, with pixel-level semantic labels for both mining-related activities and surrounding ecological structures. With this unified annotation source, we establish four benchmark tasks: semantic segmentation, segmentation-derived recognition, direct multi-label classification, and class-presence recognition with vision-language models. Across these tasks, we compare generic and remote-sensing-specific segmentation models, vision foundation model-related segmentation methods, direct multi-label classification methods, and vision-language models under a controlled closed-set protocol. Results show that current meth

Illegal, unreported, and unregulated fishing (IUU) traditionally refers to fishing activities that violate applicable laws or occur in areas that lack applicable laws. We propose the term IUU+ to capture a broader suite of fisheries sector environmental and associated supply chain trade-related crimes and behaviors. Although IUU+ activity is widely recognized as a serious threat to marine ecosystems, markets, and livelihoods, a quantitative understanding of these incidents, e.g., their frequency, geography, species, actors, and patterns in the type of illicit activity, remains difficult to obtain. We propose IUU+DB, a large language model driven system for building a global incident database of IUU+ activity. The system ingests heterogeneous documents, classifies whether they describe relevant incidents, extracts key data elements such as actors, locations, species, vessels, violations, and enforcement outcomes, and supports deduplication and trend analysis. Case studies and validation results show that IUU+DB can help organize fragmented evidence, surface geographic and behavioral hotspots, support fisheries-domain specific research in academia and non-government organizations, as

Illegal content reporting mechanisms are a key technical and organizational measure through which online platforms address illegal content under the European Union Digital Services Act (DSA). Article 16 requires user notices to be sufficiently substantiated and submitted in good faith, placing users in the difficult position of interpreting legal and procedural language and translating ambiguous content into legally meaningful categories and reasons. We investigate how large language model (LLM)-based assistants can support this reporting process. In a controlled user study (N = 450) using an interface modeled on a major platform reporting workflow, we compare three conditions: unaided reporting, a conventional explainable AI assistant (XAI) that suggests a single legal category with a rationale, and an evaluative AI assistant (EvalAI) that presents balanced pro and con arguments across candidate legal provisions. We further examine these assistance forms under systematically varied AI error regimes. Our results show that EvalAI improves provision-level accuracy under AI error and reduces misclassification distance relative to conventional XAI, particularly for near-miss and overbr

In the study, the social robot act as a patrol to recognize and notify illegal parking in real-time. Dual-model pipeline method and large multimodal model were compared, and the GPT-4o multimodal model was adopted in license plate recognition without preprocessing. For moving smoothly on a flat ground, the robot navigated in a simulated parking lot in the experiments. The robot changes angle view of the camera automatically to capture the images around with the format of license plate number. From the captured images of the robot, the numbers on the plate are recognized through the GPT-4o model, and identifies legality of the numbers. When an illegal parking is detected, the robot sends Line messages to the system manager immediately. The contribution of the work is that a novel multimodal deep learning method has validated with high accuracy in license plate recognition, and a social assistive robot is also provided for solving problems in a real scenario, and can be applied in an indoor parking lot.

This paper presents a mixed-methodology to forecast illegal border crossings in Europe across five key migratory routes, with a one-year time horizon. The methodology integrates machine learning techniques with qualitative insights from migration experts. This approach aims at improving the predictive capacity of data-driven models through the inclusion of a human-assessed covariate, an innovation that addresses challenges posed by sudden shifts in migration patterns and limitations in traditional datasets. The proposed methodology responds directly to the forecasting needs outlined in the EU Pact on Migration and Asylum, supporting the Asylum and Migration Management Regulation (AMMR). It is designed to provide policy-relevant forecasts that inform strategic decisions, early warning systems, and solidarity mechanisms among EU Member States. By joining data-driven modeling with expert judgment, this work aligns with existing academic recommendations and introduces a novel operational tool tailored for EU migration governance. The methodology is tested and validated with known data to demonstrate its applicability and reliability in migration-related policy context.

Language models trained via outcome-based reinforcement learning (RL) to reason using chain-of-thought (CoT) have shown remarkable performance. Monitoring such a model's CoT may allow us to understand its intentions and detect potential malicious behavior. However, to be effective, this requires that CoTs are legible and faithful. We study CoT legibility across 14 reasoning models, finding that RL often causes reasoning to become illegible to both humans and AI monitors, with reasoning models (except Claude) generating illegible CoTs while returning to perfectly readable final answers. We show that models use illegible reasoning to reach correct answers (accuracy dropping by 53\% when forced to use only legible portions), yet find no correlation between legibility and performance when resampling - suggesting the relationship is more nuanced. We also find that legibility degrades on harder questions. We discuss potential hypotheses for these results, including steganography, training artifacts, and vestigial tokens. These results suggest that without explicit optimization for legibility, outcome-based RL naturally produces models with increasingly opaque reasoning processes, potenti

This study investigates the defacement of Indonesian websites by actors promoting illegal online gambling. Using a lightweight methodology that combines keyword-driven dorking with systematic crawling, we identified 453 defaced webpages within one month. Although dorking alone yielded a false positive rate of approximately 20.3\%, the integration of crawling and keyword-counting enabled reliable differentiation between true and false positives. Our measurements revealed diverse defacement behaviors, including repeat defacements (150 cases), fixed instances (129), keyword modifications (55), and redirections or hidden URL injections. In total, 8,837 unique third-party URLs spanning 5,930 domains were captured, with a small subset recurring across multiple sites. Website responses were inconsistent, with an average reaction time of 75.3 hours. These findings demonstrate that simple, reproducible techniques can provide meaningful insights into the scale, persistence, and dynamics of defacement, highlighting the importance of continuous measurement for strengthening defenses against online gambling activities.

Blockchain technology, lauded for its transparent and immutable nature, introduces a novel trust model. However, its decentralized structure raises concerns about potential inclusion of malicious or illegal content. This study focuses on Ethereum, presenting a data identification and restoration algorithm. Successfully recovering 175 common files, 296 images, and 91,206 texts, we employed the FastText algorithm for sentiment analysis, achieving a 0.9 accuracy after parameter tuning. Classification revealed 70,189 neutral, 5,208 positive, and 15,810 negative texts, aiding in identifying sensitive or illicit information. Leveraging the NSFWJS library, we detected seven indecent images with 100% accuracy. Our findings expose the coexistence of benign and harmful content on the Ethereum blockchain, including personal data, explicit images, divisive language, and racial discrimination. Notably, sensitive information targeted Chinese government officials. Proposing preventative measures, our study offers valuable insights for public comprehension of blockchain technology and regulatory agency guidance. The algorithms employed present innovative solutions to address blockchain data privac

Text-to-image diffusion models can be fine-tuned in custom domains to adapt to specific user preferences, but such adaptability has also been utilized for illegal purposes, such as forging public figures' portraits, duplicating copyrighted artworks and generating explicit contents. Existing work focused on detecting the illegally generated contents, but cannot prevent or mitigate illegal adaptations of diffusion models. Other schemes of model unlearning and reinitialization, similarly, cannot prevent users from relearning the knowledge of illegal model adaptation with custom data. In this paper, we present FreezeAsGuard, a new technique that addresses these limitations and enables irreversible mitigation of illegal adaptations of diffusion models. Our approach is that the model publisher selectively freezes tensors in pre-trained diffusion models that are critical to illegal model adaptations, to mitigate the fine-tuned model's representation power in illegal adaptations, but minimize the impact on other legal adaptations. Experiment results in multiple text-to-image application domains show that FreezeAsGuard provides 37% stronger power in mitigating illegal model adaptations comp

Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order to measure the latent propensity of LLM agents for taking illegal actions under an EU legislative context, we introduce EU-Agent-Bench, a verifiable human-curated benchmark that evaluates an agent's alignment with EU legal norms in situations where benign user inputs could lead to unlawful actions. Our benchmark spans scenarios across several categories, including data protection, bias/discrimination, and scientific integrity, with each user request allowing for both compliant and non-compliant execution of the requested actions. Comparing the model's function calls against a rubric exhaustively supported by citations of the relevant legislature, we evaluate the legal compliance of frontier LLMs, and furthermore investigate the compliance effect of providing the relevant legislative excerpts in the agent's system prompt along with explicit instructions to comply. We release a public preview set for the research community, while holding out a pri

Illegal content on social media poses significant societal harm and necessitates timely removal. However, the impact of the speed of content removal on prevalence, reach, and exposure to illegal content remains underexplored. This study examines the relationship with a systematic audit of takedown delays using data from the EU Digital Services Act Transparency Database, covering five major platforms over a one-year period. We find substantial variation in takedown delay, with some content remaining online for weeks or even months. To evaluate how these delays affect the prevalence and reach of illegal content and exposure to it, we develop an agent-based model and calibrate it to empirical data. We simulate illegal content diffusion, revealing that rapid takedown (within hours) significantly reduces prevalence, reach, and exposure to illegal content, while the longer delays measured by the audit fail to reduce its spread. Though the link between delay and spread is intuitive, our simulations quantify exactly how takedown speed shapes exposure to illegal content. Building on these results, we point to the benefits of faster content removal to effectively curb the spread of illegal c

In this paper, we investigate proactive monitoring to mitigate malicious activities in integrated sensing and communication (ISAC) systems. Our focus is on a scenario where a cell-free massive multiple-input multiple-output (CF-mMIMO) architecture is exploited by malicious actors. Malicious actors use multiple access points (APs) to illegally sense a legitimate target while communicating with users (UEs), one of which is suspected of illegal activities. In our approach, a proactive monitor overhears the suspicious UE and simultaneously sends a jamming signal to degrade the communication links between the APs and suspicious UE. Simultaneously, the monitor sends a precoded jamming signal toward the legitimate target to hinder the malicious sensing attempts. We derive closed-form expressions for the sensing signal-to-interference-noise ratio (SINR), as well as the received SINR at the UEs and overheard SINR at the monitor. The simulation results show that our anti-malicious CF-mMIMO ISAC strategy can significantly reduce the sensing performance while offering excellent monitoring performance.

In our urban life, Illegal Driver Substitution (IDS) activity for a taxi is a grave unlawful activity in the taxi industry, possibly causing severe traffic accidents and painful social repercussions. Currently, the IDS activity is manually supervised by law enforcers, i.e., law enforcers empirically choose a taxi and inspect it. The pressing problem of this scheme is the dilemma between the limited number of law-enforcers and the large volume of taxis. In this paper, motivated by this problem, we propose a computational method that helps law enforcers efficiently find the taxis which tend to have the IDS activity. Firstly, our method converts the identification of the IDS activity to a supervised learning task. Secondly, two kinds of taxi driver behaviors, i.e., the Sleeping Time and Location (STL) behavior and the Pick-Up (PU) behavior are proposed. Thirdly, the multiple scale pooling on self-similarity is proposed to encode the individual behaviors into the universal features for all taxis. Finally, a Multiple Component- Multiple Instance Learning (MC-MIL) method is proposed to handle the deficiency of the behavior features and to align the behavior features simultaneously. Exten

This study introduces and examines a sophisticated malware distribution technique that exploits popular video sharing platforms. In this attack, threat actors distribute malware through deceptive content that promises free versions of premium software and game cheats. Throughout this paper, we call this attack MalTube. MalTube is particularly insidious because it exploits the guilt feelings of users for engaging in potentially illegal activity, making them less likely to report the infection or ask for a help. To investigate this emerging threat, we developed video platform exploitation reconnaissance VIPER, a novel monitoring system designed to detect, monitor, and analyze MalTube activity at scale. Over a four-month data collection period, VIPER processed and analyzed 14,363 videos, 8,671 associated channels, and 1,269 unique fully qualified domain names associated with malware downloads. Our findings reveal that MalTube attackers primarily target young gamers, using the lure of free software and game cheats as infection vectors. The attackers employ various sophisticated social engineering techniques to maximize user engagement and ensure successful malware propagation. These te

Singing voice conversion (SVC) automates song covers by converting a source singing voice from a source singer into a new singing voice with the same lyrics and melody as the source, but sounds like being covered by the target singer of some given target singing voices. However, it raises serious concerns about copyright and civil right infringements. We propose SongBsAb, the first proactive approach to tackle SVC-based illegal song covers. SongBsAb adds perturbations to singing voices before releasing them, so that when they are used, the process of SVC will be interfered, leading to unexpected singing voices. Perturbations are carefully crafted to (1) provide a dual prevention, i.e., preventing the singing voice from being used as the source and target singing voice in SVC, by proposing a gender-transformation loss and a high/low hierarchy multi-target loss, respectively; and (2) be harmless, i.e., no side-effect on the enjoyment of protected songs, by refining a psychoacoustic model-based loss with the backing track as an additional masker, a unique accompanying element for singing voices compared to ordinary speech voices. We also adopt a frame-level interaction reduction-based

Drones have been widely utilized in various fields, but the number of drones being used illegally and for hazardous purposes has increased recently. To prevent those illegal drones, in this work, we propose a novel framework for reconstructing 3D trajectories of drones using a single camera. By leveraging calibrated cameras, we exploit the relationship between 2D and 3D spaces. We automatically track the drones in 2D images using the drone tracker and estimate their 2D rotations. By combining the estimated 2D drone positions with their actual length information and camera parameters, we geometrically infer the 3D trajectories of the drones. To address the lack of public drone datasets, we also create synthetic 2D and 3D drone datasets. The experimental results show that the proposed methods accurately reconstruct drone trajectories in 3D space, and demonstrate the potential of our framework for single camera-based surveillance systems.

Image colorization is the process of colorizing grayscale images or recoloring an already-color image. This image manipulation can be used for grayscale satellite, medical and historical images making them more expressive. With the help of the increasing computation power of deep learning techniques, the colorization algorithms results are becoming more realistic in such a way that human eyes cannot differentiate between natural and colorized images. However, this poses a potential security concern, as forged or illegally manipulated images can be used illegally. There is a growing need for effective detection methods to distinguish between natural color and computer-colorized images. This paper presents a novel approach that combines the advantages of transfer and ensemble learning approaches to help reduce training time and resource requirements while proposing a model to classify natural color and computer-colorized images. The proposed model uses pre-trained branches VGG16 and Resnet50, along with Mobile Net v2 or Efficientnet feature vectors. The proposed model showed promising results, with accuracy ranging from 94.55% to 99.13% and very low Half Total Error Rate values. The

Illegal live-streaming identification, which aims to help live-streaming platforms immediately recognize the illegal behaviors in the live-streaming, such as selling precious and endangered animals, plays a crucial role in purifying the network environment. Traditionally, the live-streaming platform needs to employ some professionals to manually identify the potential illegal live-streaming. Specifically, the professional needs to search for related evidence from a large-scale knowledge database for evaluating whether a given live-streaming clip contains illegal behavior, which is time-consuming and laborious. To address this issue, in this work, we propose a multimodal evidence retrieval system, named OFAR, to facilitate the illegal live-streaming identification. OFAR consists of three modules: Query Encoder, Document Encoder, and MaxSim-based Contrastive Late Intersection. Both query encoder and document encoder are implemented with the advanced OFA encoder, which is pretrained on a large-scale multimodal dataset. In the last module, we introduce contrastive learning on the basis of the MaxiSim-based late intersection, to enhance the model's ability of query-document matching. Th