English
Related papers

Related papers: No Attack Required: Semantic Fuzzing for Specifica…

200 papers

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

Cryptography and Security · Computer Science 2026-01-16 Yi Liu , Weizhe Wang , Ruitao Feng , Yao Zhang , Guangquan Xu , Gelei Deng , Yuekang Li , Leo Zhang

Natural Language Processing (NLP) models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling…

Machine Learning · Computer Science 2025-06-10 Kasimir Schulz , Kenneth Yeung , Kieran Evans

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to prompt injections when dealing with untrusted data. To overcome this limitation, we propose…

Cryptography and Security · Computer Science 2026-01-21 Nils Philipp Walter , Chawin Sitawarin , Jamie Hayes , David Stutz , Ilia Shumailov

Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a…

Operating Systems · Computer Science 2025-10-21 Yusheng Zheng , Yanpeng Hu , Tong Yu , Andi Quinn

The rapid development of autonomous web agents powered by Large Language Models (LLMs), while greatly elevating efficiency, exposes the frontier risk of taking unintended or harmful actions. This situation underscores an urgent need for…

Artificial Intelligence · Computer Science 2025-07-22 Boyuan Zheng , Zeyi Liao , Scott Salisbury , Zeyuan Liu , Michael Lin , Qinyuan Zheng , Zifan Wang , Xiang Deng , Dawn Song , Huan Sun , Yu Su

We introduce Semantic Intent Fragmentation (SIF), an attack class against LLM orchestration systems where a single, legitimately phrased request causes an orchestrator to decompose a task into subtasks that are individually benign but…

Cryptography and Security · Computer Science 2026-04-22 Tanzim Ahad , Ismail Hossain , Md Jahangir Alam , Sai Puppala , Yoonpyo Lee , Syed Bahauddin Alam , Sajedul Talukder

This position paper argues that securing LLM agents requires first defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent. Modern LLM agents operate over an…

Cryptography and Security · Computer Science 2026-05-19 Wenjie Qu , Ming Xu , Peiran Wang , Shengfang Zhai , Jiaheng Zhang , Dawn Song

Fuzzing consists of repeatedly testing an application with modified, or fuzzed, inputs with the goal of finding security vulnerabilities in input-parsing code. In this paper, we show how to automate the generation of an input grammar…

Artificial Intelligence · Computer Science 2017-01-26 Patrice Godefroid , Hila Peleg , Rishabh Singh

This work addresses the computational challenge of enforcing privacy for agentic Large Language Models (LLMs), where privacy is governed by the contextual integrity framework. Indeed, existing defenses rely on LLM-mediated checking stages…

Cryptography and Security · Computer Science 2026-01-22 Saswat Das , Ferdinando Fioretto

The advent of large language models (LLMs) has spurred the development of numerous jailbreak techniques aimed at circumventing their security defenses against malicious attacks. An effective jailbreak approach is to identify a domain where…

Computation and Language · Computer Science 2024-11-28 Yu Peng , Zewen Long , Fangming Dong , Congyi Li , Shu Wu , Kai Chen

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…

Artificial Intelligence · Computer Science 2026-05-29 Benlong Wu , Weiming Zhang , Kejiang Chen , Han Fang , Nenghai Yu

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Cryptography and Security · Computer Science 2026-04-30 Matteo Leonesi , Francesco Belardinelli , Flavio Corradini , Marco Piangerelli

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…

Cryptography and Security · Computer Science 2026-05-18 Zheng Yan , Jingxiang Weng , Charles Chen , Dengyun Peng , Ethan Qin , Jiannan Guan , Jinhao Liu , Qiming Yu , Yixin Yuan , Fanqing Meng , Carl Che , Mengkang Hu

Test automation brings the potential to reduce costs and human effort, but several aspects of software testing remain challenging to automate. One such example is automated performance testing to find performance breaking points. Current…

Software Engineering · Computer Science 2020-08-03 Mahshid Helali Moghadam , Mehrdad Saadatmand , Markus Borg , Markus Bohlin , Björn Lisper

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed…

Cryptography and Security · Computer Science 2026-03-06 Xianglin Yang , Yufei He , Shuo Ji , Bryan Hooi , Jin Song Dong

Coverage-guided fuzzers are powerful automated bug-finding tools. They mutate program inputs, observe coverage, and save any input that hits an unexplored path for future mutation. Unfortunately, without knowledge of input formats--for…

Cryptography and Security · Computer Science 2025-07-09 Harrison Green , Claire Le Goues , Fraser Brown

Information leakage is a class of error that can lead to severe consequences. However unlike other errors, it is rarely explicitly considered during the software testing process. LeakFuzzer advances the state of the art by using a…

Software Engineering · Computer Science 2025-01-27 Daniel Blackwell , Ingolf Becker , David Clark

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Cryptography and Security · Computer Science 2025-06-02 Hanrong Zhang , Jingyuan Huang , Kai Mei , Yifei Yao , Zhenting Wang , Chenlu Zhan , Hongwei Wang , Yongfeng Zhang

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Computation and Language · Computer Science 2025-08-26 Jun Zhuang , Haibo Jin , Ye Zhang , Zhengjian Kang , Wenbin Zhang , Gaby G. Dagher , Haohan Wang

Fuzzing has become one of the most popular techniques to identify bugs in software. To improve the fuzzing process, a plethora of techniques have recently appeared in academic literature. However, evaluating and comparing these techniques…

Cryptography and Security · Computer Science 2021-08-17 David Paaßen , Sebastian Surminski , Michael Rodler , Lucas Davi