arXiv subjects

Hanna Kim

Publications and source records attributed to Hanna Kim.

9 recordsLinked to original sources

arXiv2026

SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs

Script-based malware remains a prevalent attack technique. These scripts often contain indicators of compromise (IOCs) that provide actionable threat intelligence. However, statically recovering such indicators is challenging, as relevant values may be dispersed or transformed within code. Although large language models (LLMs) have shown promise in security analysis, their ability to recover IOCs from malicious scripts remains underexplored. We present SCRIPTIOC-BENCH, a benchmark for measuring static IOC extraction capability on real-world malicious scripts. The benchmark comprises 634 manually verified JavaScript, PowerShell, and VBScript malware samples covering four IOC types (URLs, domains, IP addresses, and filesystem artifacts). We further stratify ground-truth IOCs by recovery level, distinguishing directly exposed indicators from those requiring decoding or reconstruction. Using this benchmark, we evaluate a broad range of proprietary and open-weight LLMs and show that IOC recovery without execution remains challenging across model scales: the strongest model reaches only 65.4 F1. To characterize how recovery fails, we introduce a false-positive taxonomy and use it to compare the error profiles of the evaluated models. We further study two mitigations on a small open-weight model, deterministic string utilities and task-specific adaptation, finding that they provide complementary recovery gains, raise precision, and shift errors toward sample-grounded mismatches.

cs.CR↗

arXiv2026

Learning Multi-View Spatial Reasoning from Cross-View Relations

Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems to understand 3D environments and manipulate objects across different viewpoints. In this work, we introduce Cross-View Relations (XVR), a large-scale dataset designed to teach VLMs spatial reasoning across multiple views. XVR comprises 100K vision-question-answer samples derived from 18K diverse 3D scenes and 70K robotic manipulation trajectories, spanning three fundamental spatial reasoning tasks: Correspondence (matching objects across views), Verification (validating spatial relationships), and Localization (identifying object positions). VLMs fine-tuned on XVR achieve substantial improvements on established multi-view and robotic spatial reasoning benchmarks (MindCube and RoboSpatial). When integrated as backbones in Vision-Language-Action models, XVR-trained representations improve success rates on RoboCasa. Our results demonstrate that explicit training on cross-view spatial relations significantly enhances multi-view reasoning and transfers effectively to real-world robotic manipulation.

cs.CV↗

arXiv2026

Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAG

Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with structured knowledge retrieved from a knowledge graph. While Graph RAG improves relational reasoning, it introduces a largely understudied threat: adversaries can reconstruct subgraphs from a target RAG system's knowledge graph, enabling privacy inference and replication of curated knowledge assets. We show that existing attacks are largely ineffective against Graph RAG even with simple prompt-based safeguards, because these attacks expose explicit exfiltration intent and are therefore easily suppressed by lightweight safe prompts. We identify three technical challenges for practical Graph RAG extraction under realistic safeguards and introduce GRASP, a closed-box, multi-turn subgraph reconstruction attack. GRASP (i) reframes extraction as a context-processing task, (ii) enforces format-compliant, instance-grounded outputs via per-record identifiers to reduce hallucinations and preserve relational details, and (iii) diversifies goal-driven attack queries using a discovery-aware scheduler to operate within strict query budgets. Across two real-world knowledge graphs, four safety-aligned LLMs, and multiple Graph RAG frameworks, GRASP attains the strongest type-faithful reconstruction where prior methods fail, reaching up to 82.9 F1. We further evaluate defenses and propose two mitigations that effectively reduce reconstruction fidelity without utility loss.

cs.CR↗

arXiv2026

ARGORA: Orchestrated Argumentation for Causally Grounded LLM Reasoning and Decision Making

Existing multi-expert LLM systems gather diverse perspectives but combine them through simple aggregation, obscuring which arguments drove the final decision. We introduce ARGORA, a framework that organizes multi-expert discussions into explicit argumentation graphs showing which arguments support or attack each other. By casting these graphs as causal models, ARGORA can systematically remove individual arguments and recompute outcomes, identifying which reasoning chains were necessary and whether decisions would change under targeted modifications. We further introduce a correction mechanism that aligns internal reasoning with external judgments when they disagree. Across diverse benchmarks and an open-ended use case, ARGORA achieves competitive accuracy and demonstrates corrective behavior: when experts initially disagree, the framework resolves disputes toward correct answers more often than it introduces new errors, while providing causal diagnostics of decisive arguments.

cs.AI↗

arXiv2024

When LLMs Go Online: The Emerging Threat of Web-Enabled LLMs

Recent advancements in Large Language Models (LLMs) have established them as agentic systems capable of planning and interacting with various tools. These LLM agents are often paired with web-based tools, enabling access to diverse sources and real-time information. Although these advancements offer significant benefits across various applications, they also increase the risk of malicious use, particularly in cyberattacks involving personal information. In this work, we investigate the risks associated with misuse of LLM agents in cyberattacks involving personal data. Specifically, we aim to understand: 1) how potent LLM agents can be when directed to conduct cyberattacks, 2) how cyberattacks are enhanced by web-based tools, and 3) how affordable and easy it becomes to launch cyberattacks using LLM agents. We examine three attack scenarios: the collection of Personally Identifiable Information (PII), the generation of impersonation posts, and the creation of spear-phishing emails. Our experiments reveal the effectiveness of LLM agents in these attacks: LLM agents achieved a precision of up to 95.9% in collecting PII, generated impersonation posts where 93.9% of them were deemed authentic, and boosted click rate of phishing links in spear phishing emails by 46.67%. Additionally, our findings underscore the limitations of existing safeguards in contemporary commercial LLMs, emphasizing the urgent need for robust security measures to prevent the misuse of LLM agents.

cs.CR↗

arXiv2024

Claim-Guided Textual Backdoor Attack for Practical Applications

Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor attacks require input manipulation after model distribution to activate the backdoor, posing limitations in real-world applicability. Addressing this gap, we introduce a novel Claim-Guided Backdoor Attack (CGBA), which eliminates the need for such manipulations by utilizing inherent textual claims as triggers. CGBA leverages claim extraction, clustering, and targeted training to trick models to misbehave on targeted claims without affecting their performance on clean data. CGBA demonstrates its effectiveness and stealthiness across various datasets and models, significantly enhancing the feasibility of practical backdoor attacks. Our code and data will be available at https://github.com/PaperCGBA/CGBA.

cs.CL↗

arXiv2024

Tweezers: A Framework for Security Event Detection via Event Attribution-centric Tweet Embedding

Twitter is recognized as a crucial platform for the dissemination and gathering of Cyber Threat Intelligence (CTI). Its capability to provide real-time, actionable intelligence makes it an indispensable tool for detecting security events, helping security professionals cope with ever-growing threats. However, the large volume of tweets and inherent noises of human-crafted tweets pose significant challenges in accurately identifying security events. While many studies tried to filter out event-related tweets based on keywords, they are not effective due to their limitation in understanding the semantics of tweets. Another challenge in security event detection from Twitter is the comprehensive coverage of security events. Previous studies emphasized the importance of early detection of security events, but they overlooked the importance of event coverage. To cope with these challenges, in our study, we introduce a novel event attribution-centric tweet embedding method to enable the high precision and coverage of events. Our experiment result shows that the proposed method outperforms existing text and graph-based tweet embedding methods in identifying security events. Leveraging this novel embedding approach, we have developed and implemented a framework, Tweezers, that is applicable to security event detection from Twitter for CTI gathering. This framework has demonstrated its effectiveness, detecting twice as many events compared to established baselines. Additionally, we have showcased two applications, built on Tweezers for the integration and inspection of security events, i.e., security event trend analysis and informative security user identification.

cs.CR↗

arXiv2023

DRAINCLoG: Detecting Rogue Accounts with Illegally-obtained NFTs using Classifiers Learned on Graphs

As Non-Fungible Tokens (NFTs) continue to grow in popularity, NFT users have become targets of phishing attacks by cybercriminals, called \textit{NFT drainers}. Over the last year, \$100 million worth of NFTs were stolen by drainers, and their presence remains a serious threat to the NFT trading space. However, no work has yet comprehensively investigated the behaviors of drainers in the NFT ecosystem. In this paper, we present the first study on the trading behavior of NFT drainers and introduce the first dedicated NFT drainer detection system. We collect 127M NFT transaction data from the Ethereum blockchain and 1,135 drainer accounts from five sources for the year 2022. We find that drainers exhibit significantly different transactional and social contexts from those of regular users. With these insights, we design \textit{DRAINCLoG}, an automatic drainer detection system utilizing Graph Neural Networks. This system effectively captures the multifaceted web of interactions within the NFT space through two distinct graphs: the NFT-User graph for transaction contexts and the User graph for social contexts. Evaluations using real-world NFT transaction data underscore the robustness and precision of our model. Additionally, we analyze the security of \textit{DRAINCLoG} under a wide variety of evasion attacks.

cs.CR↗

arXiv2023

A Deep Dive into NFT Whales: A Longitudinal Study of the NFT Trading Ecosystem

NFT (Non-fungible Token) has drastically increased in its size, accounting for over \$16.9B of total market capitalization. Despite the rapid growth of NFTs, this market has not been examined thoroughly from a financial perspective. In this paper, we conduct methodical analyses to identify NFT market movers who play a significant role in potentially manipulating and oscillating NFT values. We collect over 3.8M NFT transaction data from the Ethereum Blockchain from January 2021 to February 2022 to extract trading information in line with the NFT lifecycle: (i) mint, (ii) transfer/sale, and (iii) burn. Based on the size of held NFT values, we classify NFT traders into three groups (whales, dolphins, and minnows). In total, we analyze 430K traders from 91 different NFT collection sources. We find that the top 0.1\% of NFT traders (i.e., whales) drive the NFT market with consistent, high returns. We then identify and characterize the NFT whales' unique investment strategies (e.g., mint/sale patterns, wash trading) to empirically understand the whales in the NFT market for the first time.

q-fin.ST↗