arXiv subjects

Zhenkai Liang

Publications and source records attributed to Zhenkai Liang.

34 records · Page 2Linked to original sources

arXiv2025

When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation

Model Context Protocol (MCP) servers enable AI applications to connect to external systems in a plug-and-play manner, but their rapid proliferation also introduces severe security risks. Unlike mature software ecosystems with rigorous vetting, MCP servers still lack standardized review mechanisms, giving adversaries opportunities to distribute malicious implementations. Despite this pressing risk, the security implications of MCP servers remain underexplored. To address this gap, we present the first systematic study that treats MCP servers as active threat actors and decomposes them into core components to examine how adversarial developers can implant malicious intent. Specifically, we investigate three research questions: (i) what types of attacks malicious MCP servers can launch, (ii) how vulnerable MCP hosts and Large Language Models (LLMs) are to these attacks, and (iii) how feasible it is to carry out MCP server attacks in practice. Our study proposes a component-based taxonomy comprising twelve attack categories. For each category, we develop Proof-of-Concept (PoC) servers and demonstrate their effectiveness across diverse real-world host-LLM settings. We further show that attackers can generate large numbers of malicious servers at virtually no cost. We then test state-of-the-art scanners on the generated servers and found that existing detection approaches are insufficient. These findings highlight that malicious MCP servers are easy to implement, difficult to detect with current tools, and capable of causing concrete damage to AI agent systems. Addressing this threat requires coordinated efforts among protocol designers, host developers, LLM providers, and end users to build a more secure and resilient MCP ecosystem.

cs.CR↗

arXiv2025

PsyScam: A Benchmark for Psychological Techniques in Real-World Scams

Over the years, online scams have grown dramatically, with nearly 50% of global consumers encountering scam attempts each week. These scams cause not only significant financial losses to individuals and businesses, but also lasting psychological trauma, largely due to scammers' strategic employment of psychological techniques (PTs) to manipulate victims. Meanwhile, scammers continually evolve their tactics by leveraging advances in Large Language Models (LLMs) to generate diverse scam variants that easily bypass existing defenses. To address this pressing problem, we introduce PsyScam, a benchmark designed to systematically capture the PTs employed in real-world scam reports, and investigate how LLMs can be utilized to generate variants of scams based on the PTs and the contexts provided by these scams. Specifically, we collect a wide range of scam reports and ground its annotations of employed PTs in well-established cognitive and psychological theories. We further demonstrate LLMs' capabilities in generating through two downstream tasks: scam completion, and scam augmentation. Experimental results show that PsyScam presents significant challenges to existing models in both detecting and generating scam content based on the PTs used by real-world scammers. Our code and dataset are available.

cs.CR↗

arXiv2025

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues such as over-refusal and utility degradation after safety alignment. Current safety alignment methods often result in superficial refusal shortcuts or rely on intensive supervision for reasoning-based approaches, failing to fully leverage the model's intrinsic safety self-awareness. We propose \textbf{AlphaAlign}, a simple yet effective pure reinforcement learning (RL) framework with verifiable safety reward designed to incentivize this latent safety awareness through proactive safety reasoning.} AlphaAlign employs a dual-reward system: a verifiable safety reward encourages correctly formatted and explicitly justified refusals for harmful queries while penalizing over-refusals, and a normalized helpfulness reward guides high-quality responses to benign inputs. This allows the model to develop proactive safety reasoning capabilities without depending on supervised safety-specific reasoning data. AlphaAlign demonstrates three key advantages: (1) Simplicity and efficiency, requiring only binary prompt safety labels and minimal RL steps for substantial improvements. (2) Breaking the safety-utility trade-off, by enhancing refusal of harmful content and reducing over-refusals, while simultaneously maintaining or even improving general task performance and robustness to unseen jailbreaks. (3) Deep alignment, fostering proactive safety reasoning that generates explicit safety rationales rather than relying on shallow refusal patterns.

cs.AI↗

arXiv2025

Evaluating Disassembly Errors With Only Binaries

Disassemblers are crucial in the analysis and modification of binaries. Existing works showing disassembler errors largely rely on practical implementation without specific guarantees and assume source code and compiler toolchains to evaluate ground truth. However, the assumption of source code is contrary to typical binary scenarios where only the binary is available. In this work, we investigate an approach with minimal assumptions and a sound approach to disassembly error evaluation that does not require source code. Any source code does not address the fundamental problem of binary disassembly and fails when only the binary exists. As far as we know, this is the first work to evaluate disassembly errors using only the binary. We propose TraceBin, which uses dynamic execution to find disassembly errors. TraceBin targets the use case where the disassembly is used in an automated fashion for security tasks on a target binary, such as static binary instrumentation, binary hardening, automated code repair, and so on, which may be affected by disassembly errors. Discovering disassembly errors in the target binary aids in reducing problems caused by such errors. Furthermore, we are not aware of existing approaches that can evaluate errors given only a target binary, as they require source code. Our evaluation shows TraceBin finds: (i) errors consistent with existing studies even without source; (ii) disassembly errors due to control flow; (iii) new interesting errors; (iv) errors in non-C/C++ binaries; (v) errors in closed-source binaries; and (vi) show that disassembly errors can have significant security implications. Overall, our experimental results show that TraceBin finds many errors in existing popular disassemblers. It is also helpful in automated security tasks on (closed source) binaries relying on disassemblers.

cs.CR↗

arXiv2025

Signals and Symptoms: ICS Attack Dataset From Railway Cyber Range

The prevalence of cyberattacks on Industrial Control Systems (ICS) has highlighted the necessity for robust security measures and incident response to protect critical infrastructure. This is prominent when Operational Technology (OT) systems undergo digital transformation by integrating with Information Technology (IT) systems to enhance operational efficiency, adaptability, and safety. To support analysts in staying abreast of emerging attack patterns, there is a need for ICS datasets that reflect indicators representative of contemporary cyber threats. To address this, we conduct two ICS cyberattack simulations to showcase the impact of trending ICS cyberattacks on a railway cyber range that resembles the railway infrastructure. The attack scenario is designed to blend trending attack trends with attack patterns observed from historical ICS incidents. The resulting evidence is collected as datasets, serving as an essential resource for cyberattack analysis. This captures key indicators that are relevant to the current threat landscape, augmenting the effectiveness of security systems and analysts to protect against ICS cyber threats.

cs.CR↗

arXiv2025

OSS-Bench: Benchmark Generator for Coding LLMs

In light of the rapid adoption of AI coding assistants, LLM-assisted development has become increasingly prevalent, creating an urgent need for robust evaluation of generated code quality. Existing benchmarks often require extensive manual effort to create static datasets, rely on indirect or insufficiently challenging tasks, depend on non-scalable ground truth, or neglect critical low-level security evaluations, particularly memory-safety issues. In this work, we introduce OSS-Bench, a benchmark generator that automatically constructs large-scale, live evaluation tasks from real-world open-source software. OSS-Bench replaces functions with LLM-generated code and evaluates them using three natural metrics: compilability, functional correctness, and memory safety, leveraging robust signals like compilation failures, test-suite violations, and sanitizer alerts as ground truth. In our evaluation, the benchmark, instantiated as OSS-Bench(php) and OSS-Bench(sql), profiles 17 diverse LLMs, revealing insights such as intra-family behavioral patterns and inconsistencies between model size and performance. Our results demonstrate that OSS-Bench mitigates overfitting by leveraging the evolving complexity of OSS and highlights LLMs' limited understanding of low-level code security via extended fuzzing experiments. Overall, OSS-Bench offers a practical and scalable framework for benchmarking the real-world coding capabilities of LLMs.

cs.SE↗

arXiv2025

Fuzzing the PHP Interpreter via Dataflow Fusion

PHP, a dominant scripting language in web development, powers a vast range of websites, from personal blogs to major platforms. While existing research primarily focuses on PHP application-level security issues like code injection, memory errors within the PHP interpreter have been largely overlooked. These memory errors, prevalent due to the PHP interpreter's extensive C codebase, pose significant risks to the confidentiality, integrity, and availability of PHP servers. This paper introduces FlowFusion, the first automatic fuzzing framework to detect memory errors in the PHP interpreter. FlowFusion leverages dataflow as an efficient representation of test cases maintained by PHP developers, merging two or more test cases to produce fused test cases with more complex code semantics. Moreover, FlowFusion employs strategies such as test mutation, interface fuzzing, and environment crossover to increase bug finding. In our evaluation, FlowFusion found 158 unknown bugs in the PHP interpreter, with 125 fixed and 11 confirmed. Comparing FlowFusion against the official test suite and a naive test concatenation approach, FlowFusion can detect new bugs that these methods miss, while also achieving greater code coverage. FlowFusion also outperformed state-of-the-art fuzzers AFL++ and Polyglot, covering 24% more lines of code after 24 hours of fuzzing. FlowFusion has gained wide recognition among PHP developers and is now integrated into the official PHP toolchain.

cs.CR↗

arXiv2025

Enhanced Differential Testing in Emerging Database Systems

In recent years, a plethora of database management systems have surfaced to meet the demands of various scenarios. Emerging database systems, such as time-series and streaming database systems, are tailored to specific use cases requiring enhanced functionality and performance. However, as they are typically less mature, there can be bugs that either cause incorrect results or errors impacting reliability. To tackle this, we propose enhanced differential testing to uncover various bugs in emerging SQL-like database systems. The challenge is how to deal with differences of these emerging databases. Our insight is that many emerging database systems are conceptually extensions of relational database systems, making it possible to reveal logic bugs leveraging existing relational, known-reliable database systems. However, due to inevitable syntax or semantics gaps, it remains challenging to scale differential testing to various emerging database systems. We enhance differential testing for emerging database systems with three steps: (i) identifying shared clauses; (ii) extending shared clauses via mapping new features back to existing clauses of relational database systems; and (iii) generating differential inputs using extended shared clauses. We implemented our approach in a tool called SQLxDiff and applied it to four popular emerging database systems. In total, we found 57 unknown bugs, of which 17 were logic bugs and 40 were internal errors. Overall, vendors fixed 50 bugs and confirmed 5. Our results demonstrate the practicality and effectiveness of SQLxDiff in detecting bugs in emerging database systems, which has the potential to improve the reliability of their applications.

cs.SE↗

arXiv2024

MASKDROID: Robust Android Malware Detection with Masked Graph Representations

Android malware attacks have posed a severe threat to mobile users, necessitating a significant demand for the automated detection system. Among the various tools employed in malware detection, graph representations (e.g., function call graphs) have played a pivotal role in characterizing the behaviors of Android apps. However, though achieving impressive performance in malware detection, current state-of-the-art graph-based malware detectors are vulnerable to adversarial examples. These adversarial examples are meticulously crafted by introducing specific perturbations to normal malicious inputs. To defend against adversarial attacks, existing defensive mechanisms are typically supplementary additions to detectors and exhibit significant limitations, often relying on prior knowledge of adversarial examples and failing to defend against unseen types of attacks effectively. In this paper, we propose MASKDROID, a powerful detector with a strong discriminative ability to identify malware and remarkable robustness against adversarial attacks. Specifically, we introduce a masking mechanism into the Graph Neural Network (GNN) based framework, forcing MASKDROID to recover the whole input graph using a small portion (e.g., 20%) of randomly selected nodes.This strategy enables the model to understand the malicious semantics and learn more stable representations, enhancing its robustness against adversarial attacks. While capturing stable malicious semantics in the form of dependencies inside the graph structures, we further employ a contrastive module to encourage MASKDROID to learn more compact representations for both the benign and malicious classes to boost its discriminative power in detecting malware from benign apps and adversarial examples.

cs.CR↗

arXiv2024

VulZoo: A Comprehensive Vulnerability Intelligence Dataset

Software vulnerabilities pose critical security and risk concerns for many software systems. Many techniques have been proposed to effectively assess and prioritize these vulnerabilities before they cause serious consequences. To evaluate their performance, these solutions often craft their own experimental datasets from limited information sources, such as MITRE CVE and NVD, lacking a global overview of broad vulnerability intelligence. The repetitive data preparation process further complicates the verification and comparison of new solutions. To resolve this issue, in this paper, we propose VulZoo, a comprehensive vulnerability intelligence dataset that covers 17 popular vulnerability information sources. We also construct connections among these sources, enabling more straightforward configuration and adaptation for different vulnerability assessment tasks (e.g., vulnerability type prediction). Additionally, VulZoo provides utility scripts for automatic data synchronization and cleaning, relationship mining, and statistics generation. We make VulZoo publicly available and maintain it with incremental updates to facilitate future research. We believe that VulZoo serves as a valuable input to vulnerability assessment and prioritization studies. The dataset with utility scripts is available at https://github.com/NUS-Curiosity/VulZoo.

cs.CR↗

arXiv2024

KernJC: Automated Vulnerable Environment Generation for Linux Kernel Vulnerabilities

Linux kernel vulnerability reproduction is a critical task in system security. To reproduce a kernel vulnerability, the vulnerable environment and the Proof of Concept (PoC) program are needed. Most existing research focuses on the generation of PoC, while the construction of environment is overlooked. However, establishing an effective vulnerable environment to trigger a vulnerability is challenging. Firstly, it is hard to guarantee that the selected kernel version for reproduction is vulnerable, as the vulnerability version claims in online databases can occasionally be spurious. Secondly, many vulnerabilities can not be reproduced in kernels built with default configurations. Intricate non-default kernel configurations must be set to include and trigger a kernel vulnerability, but less information is available on how to recognize these configurations. To solve these challenges, we propose a patch-based approach to identify real vulnerable kernel versions and a graph-based approach to identify necessary configs for activating a specific vulnerability. We implement these approaches in a tool, KernJC, automating the generation of vulnerable environments for kernel vulnerabilities. To evaluate the efficacy of KernJC, we build a dataset containing 66 representative real-world vulnerabilities with PoCs from kernel vulnerability research in the past five years. The evaluation shows that KernJC builds vulnerable environments for all these vulnerabilities, 48.5% of which require non-default configs, and 4 have incorrect version claims in the National Vulnerability Database (NVD). Furthermore, we conduct large-scale spurious version detection on kernel vulnerabilities and identify 128 vulnerabilities which have spurious version claims in NVD. To foster future research, we release KernJC with the dataset in the community.

cs.CR↗

arXiv2024

The HitchHiker's Guide to High-Assurance System Observability Protection with Efficient Permission Switches

Protecting system observability records (logs) from compromised OSs has gained significant traction in recent times, with several note-worthy approaches proposed. Unfortunately, none of the proposed approaches achieve high performance with tiny log protection delays. They also leverage risky environments for protection (\eg many use general-purpose hypervisors or TrustZone, which have large TCB and attack surfaces). HitchHiker is an attempt to rectify this problem. The system is designed to ensure (a) in-memory protection of batched logs within a short and configurable real-time deadline by efficient hardware permission switching, and (b) an end-to-end high-assurance environment built upon hardware protection primitives with debloating strategies for secure log protection, persistence, and management. Security evaluations and validations show that HitchHiker reduces log protection delay by 93.3--99.3% compared to the state-of-the-art, while reducing TCB by 9.4--26.9X. Performance evaluations show HitchHiker incurs a geometric mean of less than 6% overhead on diverse real-world programs, improving on the state-of-the-art approach by 61.9--77.5%.

cs.CR↗

arXiv2022

AttacKG: Constructing Technique Knowledge Graph from Cyber Threat Intelligence Reports

Cyber attacks are becoming more sophisticated and diverse, making detection increasingly challenging. To combat these attacks, security practitioners actively summarize and exchange their knowledge about attacks across organizations in the form of cyber threat intelligence (CTI) reports. However, as CTI reports written in natural language texts are not structured for automatic analysis, the report usage requires tedious manual efforts of cyber threat intelligence recovery. Additionally, individual reports typically cover only a limited aspect of attack patterns (techniques) and thus are insufficient to provide a comprehensive view of attacks with multiple variants. To take advantage of threat intelligence delivered by CTI reports, we propose AttacKG to automatically extract structured attack behavior graphs from CTI reports and identify the adopted attack techniques. We then aggregate cyber threat intelligence across reports to collect different aspects of techniques and enhance attack behavior graphs into technique knowledge graphs (TKGs). In our evaluation against 1,515 real-world CTI reports from diverse intelligence sources, AttacKG effectively identifies 28,262 attack techniques with 8,393 unique Indicators of Compromises (IoCs). To further verify the accuracy of AttacKG in extracting threat intelligence, we run AttacKG on 16 manually labeled CTI reports. Empirical results show that AttacKG accurately identifies attack-relevant entities, dependencies, and techniques with F1-scores of 0.887, 0.896, and 0.789, which outperforms the state-of-the-art approaches Extractor and TTPDrill. Moreover, the unique technique-level intelligence will directly benefit downstream security tasks that rely on technique specifications, e.g., APT detection and cyber attack reconstruction.

cs.CR↗

arXiv2019

Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment

The rise of deep learning technique has raised new privacy concerns about the training data and test data. In this work, we investigate the model inversion problem in the adversarial settings, where the adversary aims at inferring information about the target model's training data and test data from the model's prediction values. We develop a solution to train a second neural network that acts as the inverse of the target model to perform the inversion. The inversion model can be trained with black-box accesses to the target model. We propose two main techniques towards training the inversion model in the adversarial settings. First, we leverage the adversary's background knowledge to compose an auxiliary set to train the inversion model, which does not require access to the original training data. Second, we design a truncation-based technique to align the inversion model to enable effective inversion of the target model from partial predictions that the adversary obtains on victim user's data. We systematically evaluate our inversion approach in various machine learning tasks and model architectures on multiple image datasets. Our experimental results show that even with no full knowledge about the target model's training data, and with only partial prediction values, our inversion approach is still able to perform accurate inversion of the target model, and outperform previous approaches.

cs.CR↗

arXiv2019

Understanding Rowhammer Attacks through the Lens of a Unified Reference Framework

Rowhammer is a hardware-based bug that allows the attacker to modify the data in the memory without accessing it, just repeatedly and frequently accessing (or hammering) physically adjacent memory rows. So that it can break the memory isolation between processes, which is seen as the cornerstone of modern system security, exposing the sensitive data to unauthorized and imperceptible corruption. A number of previous works have leveraged the rowhammer bug to achieve various critical attacks. In this work, we propose a unified reference framework for analyzing the rowhammer attacks, indicating three necessary factors in a practical rowhammer attack: the attack origin, the intended implication and the methodology. Each factor includes multiple primitives, the attacker can select primitives from three factors to constitute an effective attack. In particular, the methodology further summarizes all existing attack techniques, that are used to achieve its three primitives: Location Preparation (LP), Rapid Hammering (RH), and Exploit Verification (EV). Based on the reference framework, we analyze all previous rowhammer attacks and corresponding countermeasures. Our analysis shows that how primitives in different factors are combined and used in previous attacks, and thus points out new possibility of rowhammer attacks, enabling proactive prevention before it causes harm. Under the framework, we propose a novel expressive rowhammer attack that is capable of accumulating injected memory changes and achieving rich attack semantics. We conclude by outlining future research directions.

cs.CR↗

arXiv2016

Monet: A User-oriented Behavior-based Malware Variants Detection System for Android

Android, the most popular mobile OS, has around 78% of the mobile market share. Due to its popularity, it attracts many malware attacks. In fact, people have discovered around one million new malware samples per quarter, and it was reported that over 98% of these new malware samples are in fact "derivatives" (or variants) from existing malware families. In this paper, we first show that runtime behaviors of malware's core functionalities are in fact similar within a malware family. Hence, we propose a framework to combine "runtime behavior" with "static structures" to detect malware variants. We present the design and implementation of MONET, which has a client and a backend server module. The client module is a lightweight, in-device app for behavior monitoring and signature generation, and we realize this using two novel interception techniques. The backend server is responsible for large scale malware detection. We collect 3723 malware samples and top 500 benign apps to carry out extensive experiments of detecting malware variants and defending against malware transformation. Our experiments show that MONET can achieve around 99% accuracy in detecting malware variants. Furthermore, it can defend against 10 different obfuscation and transformation techniques, while only incurs around 7% performance overhead and about 3% battery overhead. More importantly, MONET will automatically alert users with intrusion details so to prevent further malicious behaviors.

cs.CR↗