arXiv subjects

Cen Zhang

Publications and source records attributed to Cen Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Contextualizing Sink Knowledge for Java Vulnerability Discovery

Java applications are prone to vulnerabilities stemming from the insecure use of security-sensitive APIs, such as file operations enabling path traversal or deserialization routines allowing remote code execution. These sink APIs encode critical information for vulnerability discovery: the program-specific constraints required to reach them and the exploitation conditions necessary to trigger security flaws. Despite this, existing fuzzers largely overlook such vulnerability-specific knowledge, limiting their effectiveness. We present GONDAR, a sink-centric fuzzing framework that systematically leverages sink API semantics for targeted vulnerability discovery. GONDAR first identifies reachable and exploitable sink call sites through CWE-specific scanning combined with LLM-assisted static filtering. It then deploys two specialized agents that work collaboratively with a coverage-guided fuzzer: an exploration agent generates inputs to reach target call sites by iteratively solving path constraints, while an exploitation agent synthesizes proof-of-concept exploits by reasoning about and satisfying vulnerability-triggering conditions. The agents and fuzzer continuously exchange seeds and runtime feedback, complementing each other. We evaluated GONDAR on real-world Java benchmarks, where it discovers four times more vulnerabilities than Jazzer, the state-of-the-art Java fuzzer. Notably, an earlier GONDAR version contributed to Team Atlanta's first-place CRS in the DARPA AI Cyber Challenge, and is integrated into OSS-CRS, a sandbox project in The Linux Foundation's OpenSSF, to analyze open-source Java projects, where it has already uncovered a zero-day vulnerability.

cs.CR↗

arXiv2026

OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security

DARPA's AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and open-sourced them after the competition. Yet all seven open-sourced CRSs remain largely unusable outside their original teams, each bound to the competition cloud infrastructure that no longer exists. We present OSS-CRS, an open, locally deployable framework for running and combining CRS techniques against real-world open-source projects, with budget-aware resource management. We ported the first-place system (Atlantis) and discovered 10 previously unknown bugs (three of high severity) across 8 OSS-Fuzz projects. OSS-CRS is publicly available.

cs.CR↗

arXiv2026

SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned

DARPA's AI Cyber Challenge (AIxCC, 2023--2025) is the largest competition to date for building fully autonomous cyber reasoning systems (CRSs) that leverage recent advances in AI -- particularly large language models (LLMs) -- to discover and remediate vulnerabilities in real-world open-source software. This paper presents the first systematic analysis of AIxCC. Drawing on design documents, source code, execution traces, and discussions with organizers and competing teams, we examine the competition's structure and key design decisions, characterize the architectural approaches of finalist CRSs, and analyze competition results beyond the final scoreboard. Our analysis reveals the factors that truly drove CRS performance, identifies genuine technical advances achieved by teams, and exposes limitations that remain open for future research. We conclude with lessons for organizing future competitions and broader insights toward deploying autonomous CRSs in practice.

cs.CR↗

arXiv2025

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge (AIxCC) at DEF CON 33 (August 2025). AIxCC (2023-2025) challenged teams to build autonomous cyber reasoning systems capable of discovering and patching vulnerabilities at the speed and scale of modern software. ATLANTIS integrates large language models (LLMs) with program analysis -- combining symbolic execution, directed fuzzing, and static analysis -- to address limitations in automated vulnerability discovery and program repair. Developed by researchers at Georgia Institute of Technology, Samsung Research, KAIST, and POSTECH, the system addresses core challenges: scaling across diverse codebases from C to Java, achieving high precision while maintaining broad coverage, and producing semantically correct patches that preserve intended behavior. We detail the design philosophy, architectural decisions, and implementation strategies behind ATLANTIS, share lessons learned from pushing the boundaries of automated security when program analysis meets modern AI, and release artifacts to support reproducibility and future research.

cs.CR↗

arXiv2025

Smart Contract Fuzzing Towards Profitable Vulnerabilities

Billions of dollars are transacted through smart contracts, making vulnerabilities a major financial risk. One focus in the security arms race is on profitable vulnerabilities that attackers can exploit. Fuzzing is a key method for identifying these vulnerabilities. However, current solutions face two main limitations: a lack of profit-centric techniques for expediting detection, and insufficient automation in maximizing the profitability of discovered vulnerabilities, leaving the analysis to human experts. To address these gaps, we have developed VERITE, a profit-centric smart contract fuzzing framework that not only effectively detects those profitable vulnerabilities but also maximizes the exploited profits. VERITE has three key features: 1) DeFi action-based mutators for boosting the exploration of transactions with different fund flows; 2) potentially profitable candidates identification criteria, which checks whether the input has caused abnormal fund flow properties during testing; 3) a gradient descent-based profit maximization strategy for these identified candidates. VERITE is fully developed from scratch and evaluated on a dataset consisting of 61 exploited real-world DeFi projects with an average of over 1.1 million dollars loss. The results show that VERITE can automatically extract more than 18 million dollars in total and is significantly better than state-of-the-art fuzzer ITYFUZZ in both detection (29/10) and exploitation (134 times more profits gained on average). Remarkably, in 12 targets, it gains more profits than real-world attacking exploits (1.01 to 11.45 times more). VERITE is also applied by auditors in contract auditing, where 6 (5 high severity) zero-day vulnerabilities are found with over $2,500 bounty rewards.

cs.CR↗

arXiv2024

LLM Based Input Space Partitioning Testing for Library APIs

Automated library APIs testing is difficult as it requires exploring a vast space of parameter inputs that may involve objects with complex data types. Existing search based approaches, with limited knowledge of relations between object states and program branches, often suffer from the low efficiency issue, i.e., tending to generate invalid inputs. Symbolic execution based approaches can effectively identify such relations, but fail to scale to large programs. In this work, we present an LLM-based input space partitioning testing approach, LISP, for library APIs. The approach leverages LLMs to understand the code of a library API under test and perform input space partitioning based on its understanding and rich common knowledge. Specifically, we provide the signature and code of the API under test to LLMs, with the expectation of obtaining a text description of each input space partition of theAPI under test. Then, we generate inputs through employing the generated text description to sample inputs from each partition, ultimately resulting in test suites that systematically explore the program behavior of the API. We evaluate LISP on more than 2,205 library API methods taken from 10 popular open-source Java libraries (e.g.,apache/commonslang with 2.6k stars, guava with 48.8k stars on GitHub). Our experiment results show that LISP is effective in library API testing. It significantly outperforms state-of-the-art tool EvoSuite in terms of edge coverage. On average, LISP achieves 67.82% branch coverage, surpassing EvoSuite by 1.21 times. In total, LISP triggers 404 exceptions or errors in the experiments, and discovers 13 previously unknown vulnerabilities during evaluation, which have been assigned CVE IDs.

cs.SE↗

arXiv2024

GUNet: A Graph Convolutional Network United Diffusion Model for Stable and Diversity Pose Generation

Pose skeleton images are an important reference in pose-controllable image generation. In order to enrich the source of skeleton images, recent works have investigated the generation of pose skeletons based on natural language. These methods are based on GANs. However, it remains challenging to perform diverse, structurally correct and aesthetically pleasing human pose skeleton generation with various textual inputs. To address this problem, we propose a framework with GUNet as the main model, PoseDiffusion. It is the first generative framework based on a diffusion model and also contains a series of variants fine-tuned based on a stable diffusion model. PoseDiffusion demonstrates several desired properties that outperform existing methods. 1) Correct Skeletons. GUNet, a denoising model of PoseDiffusion, is designed to incorporate graphical convolutional neural networks. It is able to learn the spatial relationships of the human skeleton by introducing skeletal information during the training process. 2) Diversity. We decouple the key points of the skeleton and characterise them separately, and use cross-attention to introduce textual conditions. Experimental results show that PoseDiffusion outperforms existing SoTA algorithms in terms of stability and diversity of text-driven pose skeleton generation. Qualitative analyses further demonstrate its superiority for controllable generation in Stable Diffusion.

cs.CV↗

arXiv2024

Semantic-Enhanced Indirect Call Analysis with Large Language Models

In contemporary software development, the widespread use of indirect calls to achieve dynamic features poses challenges in constructing precise control flow graphs (CFGs), which further impacts the performance of downstream static analysis tasks. To tackle this issue, various types of indirect call analyzers have been proposed. However, they do not fully leverage the semantic information of the program, limiting their effectiveness in real-world scenarios. To address these issues, this paper proposes Semantic-Enhanced Analysis (SEA), a new approach to enhance the effectiveness of indirect call analysis. Our fundamental insight is that for common programming practices, indirect calls often exhibit semantic similarity with their invoked targets. This semantic alignment serves as a supportive mechanism for static analysis techniques in filtering out false targets. Notably, contemporary large language models (LLMs) are trained on extensive code corpora, encompassing tasks such as code summarization, making them well-suited for semantic analysis. Specifically, SEA leverages LLMs to generate natural language summaries of both indirect calls and target functions from multiple perspectives. Through further analysis of these summaries, SEA can determine their suitability as caller-callee pairs. Experimental results demonstrate that SEA can significantly enhance existing static analysis methods by producing more precise target sets for indirect calls.

cs.SE↗

arXiv2024

Evaluating Large Language Models for Line-Level Vulnerability Localization

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in line-level vulnerability localization remains underexplored. In this work, we present the first comprehensive empirical evaluation of LLMs for AVL. Our study examines 19 leading LLMs suitable for code analysis, including ChatGPT and multiple open-source models, spanning encoder-only, encoder-decoder, and decoder-only architectures, with model sizes from 60M to 70B parameters. We evaluate three paradigms including few-shot prompting, discriminative fine-tuning, and generative fine-tuning with and without Low-Rank Adaptation (LoRA), on both a BigVul-derived dataset for C/C++ and a smart contract vulnerability dataset.} Our results show that discriminative fine-tuning achieves substantial performance gains over existing learning-based AVL methods when sufficient training data is available. In low-data settings, prompting advanced LLMs such as ChatGPT proves more effective. We also identify challenges related to input length and unidirectional context during fine-tuning, and propose two remedial strategies: a sliding window approach and right-forward embedding, both of which yield significant improvements. Moreover, we provide the first assessment of LLM generalizability in AVL, showing that certain models can transfer effectively across Common Weakness Enumerations (CWEs) and projects. However, performance degrades notably for newly discovered vulnerabilities containing unfamiliar lexical or structural patterns, underscoring the need for continual adaptation.

cs.SE↗

arXiv2024

DeepFWI: Identifying Bug-Sensitive Warnings with Multi-Modal Code-Warning Semantics

Static analysis tools have evolved over time to assist in detecting bugs. However, the excessive false warnings can impede developers' productivity and confidence in the tools. Previous research efforts have explored learning-based approaches to identify bug warnings. Nevertheless, their coarse granularity, focusing on either long-term warnings or function-level alerts, is insensitive to individual bugs. Also, they rely on manually crafted features or solely on source code semantics, which is inadequate for effective learning. In this paper, we propose DeepFWI, a learning-based approach that identifies bug-sensitive warnings at a fine-grained granularity. Specifically, we design a novel LSTM-based model that captures multi-modal semantics of source code and warnings from automated static analysis tools (ASATs) and highlights their correlations with cross-attention. To tackle the data scarcity of training and evaluation, we collected a large-scale dataset of 280,273 warnings. We conducted extensive experiments on the dataset to evaluate DeepFWI. The experimental results demonstrate the effectiveness of our approach, with an F1-score 67.06% for confirming true warnings in a finer-grained manner, significantly outperforming all baselines. Additionally, to validate the practicality of DeepFWI from the perspective of developers, we applied DeepFWI to four popular open-source projects. Our approach filtered out the vast majority of warnings, while still successfully surfacing 25 true bug-related warnings that were confirmed through manual analysis.

cs.SE↗

arXiv2024

A Survey of Protocol Fuzzing

Communication protocols form the bedrock of our interconnected world, yet vulnerabilities within their implementations pose significant security threats. Recent developments have seen a surge in fuzzing-based research dedicated to uncovering these vulnerabilities within protocol implementations. However, there still lacks a systematic overview of protocol fuzzing for answering the essential questions such as what the unique challenges are, how existing works solve them, etc. To bridge this gap, we conducted a comprehensive investigation of related works from both academia and industry. Our study includes a detailed summary of the specific challenges in protocol fuzzing, and provides a systematic categorization and overview of existing research efforts. Furthermore, we explore and discuss potential future research directions in protocol fuzzing. This survey serves as a foundational guideline for researchers and practitioners in the field.

cs.CR↗

arXiv2023

JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks

The systems and software powered by Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vulnerable to prompt-based attacks, with jailbreaking attacks enabling the LLM system to generate harmful content, while hijacking attacks manipulate the LLM system to perform attacker-desired tasks, underscoring the necessity for detection tools. Unfortunately, existing detecting approaches are usually tailored to specific attacks, resulting in poor generalization in detecting various attacks across different modalities. To address it, we propose JailGuard, a universal detection framework deployed on top of LLM systems for prompt-based attacks across text and image modalities. JailGuard operates on the principle that attacks are inherently less robust than benign ones. Specifically, JailGuard mutates untrusted inputs to generate variants and leverages the discrepancy of the variants' responses on the target model to distinguish attack samples from benign samples. We implement 18 mutators for text and image inputs and design a mutator combination policy to further improve detection generalization. The evaluation on the dataset containing 15 known attack types suggests that JailGuard achieves the best detection accuracy of 86.14%/82.90% on text and image inputs, outperforming state-of-the-art methods by 11.81%-25.73% and 12.20%-21.40%.

cs.CR↗

arXiv2023

EndWatch: A Practical Method for Detecting Non-Termination in Real-World Software

Detecting non-termination is crucial for ensuring program correctness and security, such as preventing denial-of-service attacks. While termination analysis has been studied for many years, existing methods have limited scalability and are only effective on small programs. To address this issue, we propose a practical termination checking technique, called EndWatch, for detecting non-termination caused by infinite loops through testing. Specifically, we introduce two methods to generate non-termination oracles based on checking state revisits, i.e., if the program returns to a previously visited state at the same program location, it does not terminate. The non-termination oracles can be incorporated into testing tools (e.g., AFL used in this paper) to detect non-termination in large programs. For linear loops, we perform symbolic execution on individual loops to infer State Revisit Conditions (SRCs) and instrument SRCs into target loops. For non-linear loops, we instrument target loops for checking concrete state revisits during execution. We evaluated EndWatch on standard benchmarks with small-sized programs and real-world projects with large-sized programs. The evaluation results show that EndWatch is more effective than the state-of-the-art tools on standard benchmarks (detecting 87% of non-terminating programs while the best baseline detects only 67%), and useful in detecting non-termination in real-world projects (detecting 90% of known non-termination CVEs and 4 unknown bugs).

cs.SE↗

arXiv2023

ASTER: Automatic Speech Recognition System Accessibility Testing for Stutterers

The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility of ASR systems for stutterers, we need to expose and analyze the failures of ASR systems on stuttering speech. The speech datasets recorded from stutterers are not diverse enough to expose most of the failures. Furthermore, these datasets lack ground truth information about the non-stuttered text, rendering them unsuitable as comprehensive test suites. Therefore, a methodology for generating stuttering speech as test inputs to test and analyze the performance of ASR systems is needed. However, generating valid test inputs in this scenario is challenging. The reason is that although the generated test inputs should mimic how stutterers speak, they should also be diverse enough to trigger more failures. To address the challenge, we propose ASTER, a technique for automatically testing the accessibility of ASR systems. ASTER can generate valid test cases by injecting five different types of stuttering. The generated test cases can both simulate realistic stuttering speech and expose failures in ASR systems. Moreover, ASTER can further enhance the quality of the test cases with a multi-objective optimization-based seed updating algorithm. We implemented ASTER as a framework and evaluated it on four open-source ASR models and three commercial ASR systems. We conduct a comprehensive evaluation of ASTER and find that it significantly increases the word error rate, match error rate, and word information loss in the evaluated ASR systems. Additionally, our user study demonstrates that the generated stuttering audio is indistinguishable from real-world stuttering audio clips.

cs.SD↗

arXiv2023

How Effective Are They? Exploring Large Language Model Based Fuzz Driver Generation

LLM-based (Large Language Model) fuzz driver generation is a promising research area. Unlike traditional program analysis-based method, this text-based approach is more general and capable of harnessing a variety of API usage information, resulting in code that is friendly for human readers. However, there is still a lack of understanding regarding the fundamental issues on this direction, such as its effectiveness and potential challenges. To bridge this gap, we conducted the first in-depth study targeting the important issues of using LLMs to generate effective fuzz drivers. Our study features a curated dataset with 86 fuzz driver generation questions from 30 widely-used C projects. Six prompting strategies are designed and tested across five state-of-the-art LLMs with five different temperature settings. In total, our study evaluated 736,430 generated fuzz drivers, with 0.85 billion token costs ($8,000+ charged tokens). Additionally, we compared the LLM-generated drivers against those utilized in industry, conducting extensive fuzzing experiments (3.75 CPU-year). Our study uncovered that: - While LLM-based fuzz driver generation is a promising direction, it still encounters several obstacles towards practical applications; - LLMs face difficulties in generating effective fuzz drivers for APIs with intricate specifics. Three featured design choices of prompt strategies can be beneficial: issuing repeat queries, querying with examples, and employing an iterative querying process; - While LLM-generated drivers can yield fuzzing outcomes that are on par with those used in the industry, there are substantial opportunities for enhancement, such as extending contained API usage, or integrating semantic oracles to facilitate logical bug detection. Our insights have been implemented to improve the OSS-Fuzz-Gen project, facilitating practical fuzz driver generation in industry.

cs.CR↗

arXiv2023

Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs

Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are effective but limited by language specificity and weak cross-language generalization. Large language models (LLMs) are promising for code tasks, yet their capabilities for fundamental code analysis remain underexplored. We structure our study around three aspects aligned with human practices: syntax parsing, static semantics inference, and dynamic reasoning. We evaluate 21 state-of-the-art LLMs across nine tasks in four languages (C, Java, Python, Solidity), including AST generation, CFG construction, data dependency, taint analysis, and flaky test reasoning. We apply a three-layer evaluation protocol (automated metrics, expert adjudication, consistency validation) to 3,124 code samples, achieving high inter-rater reliability (Cohen's kappa = 0.844-0.936) and strong human-machine agreement (Gwet's AC1 = 0.500-0.727, F1 = 0.791-0.882). While the best LLMs excel in syntax parsing (AST 90%+, expression matching 84-100%) and show promise in static analysis, their dynamic reasoning remains limited (<70%) with high data-shift sensitivity (per-project F1 varying 0-1.0). This hierarchy holds across model families and scales, suggesting fundamental rather than transient limitations. These findings show how LLMs complement traditional analyzers: they offer cross-language generalization but non-deterministic outputs needing validation, while traditional tools give deterministic guarantees but need language-specific configuration. We contribute a validated evaluation framework with comparison against traditional analyzers (Tree-sitter, Soot, Joern) and task-specific applicability tiers. Benchmark: https://github.com/mathieu0905/llm_code_analysis.git

cs.SE↗

arXiv2022

Truncation, validity, uncertainties

The truncation of the standard-model effective field theory, its validity and the associated uncertainties have been discussed in meetings of the LHC EFT WG. Proposals were made by participants to address these issues. No consensus was reached and no formal recommendation is therefore put forward at this time. None of the proposals has been approved or validated and further work is needed to establish a prescription. This note aims at summarizing the proposals and points of debate.

hep-ph↗

arXiv2022

Moments for positivity: using Drell-Yan data to test positivity bounds and reverse-engineer new physics

Moments of the leptonic angular distribution in the Drell-Yan process have recently been shown to be sensitive probes of a specific class of dimension-8, four-fermion operators in the Standard Model Effective Field Theory, involving a pair of quarks and leptons. The same operators are also subject to positivity bounds, when requiring the associated (unknown) UV completion to obey basic principles of quantum field theory. We perform a phenomenological study to quantify the sensitivity of the high-luminosity LHC to this set of operators and, by extension, the positivity bounds. We further extend the angular basis of moments and consider double differential information to improve the ability to disentangle the different operators, leading to a sensitivity to new physics scales up to 3 TeV. We use this information to explore the violation of positivity at the LHC as a way to test the underlying principles of quantum field theory. Finally, we present a case study which combines our results with information from other (current and prospective) experiments, as well as the positivity cone to infer the properties of possible tree-level UV completions. The data lead to robust, model-independent lower bounds on the $M/\sqrt{g}$ combination of the particle mass and coupling, for states that couple to right-handed leptons and/or up quarks.

hep-ph↗