English
Related papers

Related papers: TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing f…

200 papers

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…

Cryptography and Security · Computer Science 2026-02-06 Zihan Wang , Hongwei Li , Rui Zhang , Wenbo Jiang , Guowen Xu

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Cryptography and Security · Computer Science 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

Fuzzing is effective for vulnerability discovery but struggles with complex targets such as compilers, interpreters, and database engines, which accept textual input that must satisfy intricate syntactic and semantic constraints. Although…

Cryptography and Security · Computer Science 2025-09-26 Jiayi Lin , Liangcai Su , Junzhe Li , Chenxiong Qian

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

Cryptography and Security · Computer Science 2024-09-10 Divyanshu Kumar , Anurakt Kumar , Sahil Agarwal , Prashanth Harshangi

Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like buffer overflows and use-after-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries such as…

Software Engineering · Computer Science 2025-01-09 Kunpeng Zhang , Shuai Wang , Jitao Han , Xiaogang Zhu , Xian Li , Shaohua Wang , Sheng Wen

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Cryptography and Security · Computer Science 2025-10-06 Zachary Coalson , Jeonghyun Woo , Chris S. Lin , Joyce Qu , Yu Sun , Shiyang Chen , Lishan Yang , Gururaj Saileshwar , Prashant Nair , Bo Fang , Sanghyun Hong

Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I…

Cryptography and Security · Computer Science 2025-11-07 Shiyin Lin

Taint-style vulnerabilities comprise a majority of fuzzer discovered program faults. These vulnerabilities usually manifest as memory access violations caused by tainted program input. Although fuzzers have helped uncover a majority of…

Cryptography and Security · Computer Science 2017-06-02 Bhargava Shastry , Federico Maggi , Fabian Yamaguchi , Konrad Rieck , Jean-Pierre Seifert

Fuzzing has become a widely adopted technique for vulnerability discovery, yet it remains ineffective for structured-input programs due to strict syntactic constraints and limited semantic awareness. Traditional greybox fuzzers rely on…

Cryptography and Security · Computer Science 2026-04-21 Yihao Zou , Tianming Zheng , Futai Zou , Yue Wu

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

Cryptography and Security · Computer Science 2025-08-26 Wei Jie Yeo , Ranjan Satapathy , Erik Cambria

While Large Language Models (LLMs) have achieved remarkable progress, they remain vulnerable to jailbreak attacks. Existing methods, primarily relying on discrete input optimization (e.g., GCG), often suffer from high computational costs…

Computation and Language · Computer Science 2026-01-09 Wenpeng Xing , Mohan Li , Chunqiang Hu , Haitao Xu , Ningyu Zhang , Bo Lin , Meng Han

Large language models (LLM) have achieved impressive performance on medical question-answering benchmarks. However, high benchmark accuracy does not imply that the performance generalizes to real-world clinical settings. Medical…

Computation and Language · Computer Science 2024-09-04 Robert Osazuwa Ness , Katie Matton , Hayden Helm , Sheng Zhang , Junaid Bajwa , Carey E. Priebe , Eric Horvitz

A fundamental problem in cybersecurity and computer science is determining whether a program is free of bugs and vulnerabilities. Fuzzing, a popular approach to discovering vulnerabilities in programs, has several advantages over…

Cryptography and Security · Computer Science 2026-01-27 Ian Hardgrove , John D. Hastings

Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) services due to their exceptional proficiency in understanding and generating human-like text. LLM chatbots, in particular, have seen widespread adoption,…

Cryptography and Security · Computer Science 2024-02-14 Gelei Deng , Yi Liu , Yuekang Li , Kailong Wang , Ying Zhang , Zefeng Li , Haoyu Wang , Tianwei Zhang , Yang Liu

Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However,…

Cryptography and Security · Computer Science 2026-05-20 Hongyu Cai , Arjun Arunasalam , Yiming Liang , Antonio Bianchi , Z. Berkay Celik

While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic…

Software Engineering · Computer Science 2026-02-13 Ziyi Yang , Kalit Inani , Keshav Kabra , Vima Gupta , Anand Padmanabha Iyer

Greybox fuzzing is one of the most popular methods for detecting software vulnerabilities, which conducts a biased random search within the program input space. To enhance its effectiveness in achieving deep coverage of program behaviors,…

Software Engineering · Computer Science 2026-05-06 Ruijie Meng , Gregory J. Duck , Abhik Roychoudhury

Traditional protocol fuzzing techniques, such as those employed by AFL-based systems, often lack effectiveness due to a limited semantic understanding of complex protocol grammars and rigid seed mutation strategies. Recent works, such as…

Cryptography and Security · Computer Science 2025-08-21 Youssef Maklad , Fares Wael , Ali Hamdi , Wael Elsersy , Khaled Shaban

Real-world programs expecting structured inputs often has a format-parsing stage gating the deeper program space. Neither a mutation-based approach nor a generative approach can provide a solution that is effective and scalable. Large…

Cryptography and Security · Computer Science 2023-06-13 Jie Hu , Qian Zhang , Heng Yin