arXiv subjects

Junmin Zhu

Publications and source records attributed to Junmin Zhu.

5 recordsLinked to original sources

arXiv2026

SeedSmith: LLM-Driven Seed Synthesis for Directed Fuzzing

Directed fuzzing steers fuzzers toward user-defined sink functions to identify vulnerabilities, but it frequently fails to trigger crashes even after long campaigns. We identify two challenges that prevent directed fuzzers from exposing crashes: incomplete static analysis of indirect calls, which leaves reachable paths invisible to distance-based guidance, and lack of semantic guidance for crash preconditions, which blind mutation cannot satisfy within practical time budgets. A natural intervention point is the initial seed corpus: seeds that encode the right control-flow path and satisfy key crash preconditions shift fuzzing from blind exploration to local refinement. Existing seed generation approaches address neither: grammar-based and format-driven methods produce structurally valid inputs with no sink awareness, while LLM-based methods either lack sink targeting or inherit static analysis limitations through one-shot prompting. We present SeedSmith, an agentic LLM pipeline that replicates a security analyst's workflow: starting from a sink, it iteratively explores the codebase, resolves indirect calls, identifies crash preconditions, and synthesizes concrete inputs that satisfy them. Because SeedSmith operates as a seed generation front-end, its seeds are fuzzer-agnostic and improve any downstream mutation-based fuzzer without modification. On Magma, fuzzers using SeedSmith seeds achieve geometric mean crash-time speedups of 11.51 times (AFL++) to 14.66 times (AFLGo) over default seeds. On ARVO, SeedSmith enables fuzzers to trigger 16 previously unreachable bugs spanning 10 projects with diverse input formats.

cs.CR↗

arXiv2026

LongNovel: A Multi-Scale Benchmark for Hallucination Detection in Long-Context Novel Summarization

Although context windows have expanded significantly in recent years, hallucinations in long-context summarization remain a challenge. Long novels are better suited than news or papers for researching these hallucinations, due to their intrinsic information and detailed descriptions of events and dialogues. However, current research lacks a multi-scale benchmark for hallucination detection in long-context novel summarization and does not fully explore how hallucinations change as the context grows longer. In this study, we propose LongNovel, a multi-scale long-context bilingual (Chinese and English) novel benchmark for hallucination detection. This benchmark is constructed from 29 Chinese novels (ranging from 16k to 100k tokens) and chapter-level data from the BookSum dataset. We design 8 hallucination types and employ a combination of Multi-Model Arbitration and Entity-Referenced Hallucination Generation to ensure both data authenticity and a balanced distribution of hallucination categories. Furthermore, we manually revise the content in the test set to guarantee data reliability. Extensive experimental results demonstrate that LongNovel is a challenging benchmark. We release LongNovel for future research. https://github.com/BDML-lab/LongNovel

cs.CL↗

arXiv2024

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels

Large language models (LLMs) have been well-researched in various long-context tasks. However, the scarcity of long-context summarization datasets hinders progress in this area. To address this, we introduce CNNSum, a multi-scale long-context summarization benchmark based on Chinese novels, featuring human-driven annotations across four subsets totaling 695 samples, with lengths ranging from 16k to 128k. We benchmark numerous LLMs and conduct detailed human assessments to summarize abnormal output types. Furthermore, we extensively explore how to improve long-context summarization. In our study: (1) Advanced LLMs may generate much subjective commentary, leading to vague summaries. (2) Currently, long-context summarization mainly relies on memory ability. The advantages of Large LLMs are hard to utilize, thus small LLMs are more cost-effective. (3) Different prompt types paired with various version models may cause large performance gaps. In further fine-tuning, these can be mitigated, and the Base version models perform better. (4) LLMs with RoPE-base scaled exhibit strong extrapolation potential; using short-context data can significantly improve long-context summarization performance. However, further applying other interpolation methods requires careful selection. (5) CNNSum provides more reliable evaluation results than other benchmarks. We release CNNSum to advance future research.(https://github.com/CxsGhost/CNNSum)

cs.CL↗

arXiv2024

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios

As Large Language Models (LLMs) evolve in natural language processing (NLP), their ability to stably follow instructions in long-context inputs has become critical for real-world applications. However, existing benchmarks seldom focus on instruction-following in long-context scenarios or stability on different inputs. To bridge this gap, we introduce LIFBench, a scalable dataset designed to evaluate LLMs' instruction-following capabilities and stability across long contexts. LIFBench comprises three long-context scenarios and eleven diverse tasks, featuring 2,766 instructions generated through an automated expansion method across three dimensions: length, expression, and variables. For evaluation, we propose LIFEval, a rubric-based assessment method that enables precise, automated scoring of complex LLM responses without reliance on LLM-assisted assessments or human judgment. This method allows for a comprehensive analysis of model performance and stability from multiple perspectives. We conduct detailed experiments on 20 prominent LLMs across six length intervals. Our work contributes LIFBench and LIFEval as robust tools for assessing LLM performance in complex and long-context settings, offering valuable insights to guide future advancements in LLM development.

cs.CL↗

arXiv2023

Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs

The emergence of large language models (LLMs) has significantly accelerated the development of a wide range of applications across various fields. There is a growing trend in the construction of specialized platforms based on LLMs, such as the newly introduced custom GPTs by OpenAI. While custom GPTs provide various functionalities like web browsing and code execution, they also introduce significant security threats. In this paper, we conduct a comprehensive analysis of the security and privacy issues arising from the custom GPT platform. Our systematic examination categorizes potential attack scenarios into three threat models based on the role of the malicious actor, and identifies critical data exchange channels in custom GPTs. Utilizing the STRIDE threat modeling framework, we identify 26 potential attack vectors, with 19 being partially or fully validated in real-world settings. Our findings emphasize the urgent need for robust security and privacy measures in the custom GPT ecosystem, especially in light of the forthcoming launch of the official GPT store by OpenAI.

cs.CR↗