English
Related papers

Related papers: Continuous Discovery of Vulnerabilities in LLM Ser…

200 papers

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV)…

Machine Learning · Computer Science 2026-05-07 Chengyi Nie , Nian Si , Zijie Zhou

Greybox fuzzing has achieved success in revealing bugs and vulnerabilities in programs. However, randomized mutation strategies have limited the fuzzer's performance on structured data. Specialized fuzzers can handle complex structured…

Cryptography and Security · Computer Science 2026-03-18 Hongxiang Zhang , Yuyang Rong , Yifeng He , Hao Chen

Graph algorithms, such as shortest path finding, play a crucial role in enabling essential applications and services like infrastructure planning and navigation, making their correctness important. However, thoroughly testing graph…

Software Engineering · Computer Science 2025-02-24 Wenqi Yan , Manuel Rigger , Anthony Wirth , Van-Thuan Pham

Large language models (LLMs) have recently experienced tremendous popularity and are widely used from casual conversations to AI-driven programming. However, despite their considerable success, LLMs are not entirely reliable and can give…

Artificial Intelligence · Computer Science 2024-06-28 Jiahao Yu , Xingwei Lin , Zheng Yu , Xinyu Xing

Fuzzing is a highly effective automated testing method for uncovering software vulnerabilities. Despite advances in fuzzing techniques, such as coverage-guided greybox fuzzing, many fuzzers struggle with coverage plateaus caused by fuzz…

Software Engineering · Computer Science 2025-10-07 Wentao Gao , Renata Borovica-Gajic , Sang Kil Cha , Tian Qiu , Van-Thuan Pham

The security of modern JavaScript (JS) engines is critical since they provide the primary defense mechanism for executing untrusted code on the web. The recent integration of WebAssembly (Wasm) has transformed these engines into complex…

Cryptography and Security · Computer Science 2026-03-20 Lingming Zhang , Binbin Zhao , Puzhuo Liu , Qinge Xie , Peng Di , Jianhai Chen , Shouling Ji

Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversaries infer sensitive user inputs from shared entries, leading…

Cryptography and Security · Computer Science 2026-02-11 Kexin Chu , Zecheng Lin , Dawei Xiang , Zixu Shen , Jianchang Su , Cheng Chu , Yiwei Yang , Wenhui Zhang , Wenfei Wu , Wei Zhang

Over 70% of security vulnerabilities in critical software systems today result from memory safety violations. To address this challenge, fuzzing and static analysis are widely used automated methods to discover such vulnerabilities. Fuzzing…

Cryptography and Security · Computer Science 2026-03-31 Keno Hassler , Philipp Görz , Stephan Lipp

Testing-based methodologies like fuzzing are able to analyze complex software which is not amenable to traditional formal approaches like verification, model checking, and abstract interpretation. Despite enormous success at exposing…

Software Engineering · Computer Science 2019-04-17 Shaobo He , Michael Emmi , Gabriela Ciocarlie

Fuzzing is widely used for software vulnerability detection. There are various kinds of fuzzers with different fuzzing strategies, and most of them perform well on their targets. However, in industry practice and empirical study, the…

Software Engineering · Computer Science 2019-05-07 Yuanliang Chen , Yu Jiang , Fuchen Ma , Jie Liang , Mingzhe Wang , Chijin Zhou , Zhuo Su , Xun Jiao

Fuzzing has become one of the most effective bug finding approach for software. In recent years, 24*7 continuous fuzzing platforms have emerged to test critical pieces of software, e.g., Linux kernel. Though capable of discovering many bugs…

Cryptography and Security · Computer Science 2021-11-12 Xiaochen Zou , Guoren Li , Weiteng Chen , Hang Zhang , Zhiyun Qian

Directed greybox fuzzing (DGF) aims to efficiently trigger bugs at specific target locations by prioritizing seeds whose execution paths are more likely to reach the targets. However, existing DGF approaches suffer from imprecise potential…

Cryptography and Security · Computer Science 2026-02-03 Yifan Zhang , Xin Zhang

Large Language Models(LLMs) are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all tokens as equally important during…

Cryptography and Security · Computer Science 2026-03-25 Wenyu Chen , Xiangtao Meng , Chuanchao Zang , Li Wang , Xinyu Gao , Jianing Wang , Peng Zhan , Zheng Li , Shanqing Guo

Grey box fuzzing is one of the most successful methods for automatic vulnerability detection. However,conventional Grey box Fuzzers like AFL can open perform fuzzing against the whole input and spend more time on smaller seeds with lower…

Cryptography and Security · Computer Science 2022-03-31 Linlin Zhang , Ning Luo

This review report discusses the cold start latency in serverless inference and existing solutions. It particularly reviews the ServerlessLLM method, a system designed to address the cold start problem in serverless inference for large…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-26 Himel Ghosh

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

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

Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to elicit harmful outputs, poses significant security risks.…

Cryptography and Security · Computer Science 2026-04-15 Qingchao Shen , Zibo Xiao , Lili Huang , Enwei Hu , Yongqiang Tian , Junjie Chen

Coverage-based graybox fuzzer (CGF), such as AFL has gained great success in vulnerability detection thanks to its ease-of-use and bug-finding power. Since some code fragments such as memory allocation are more vulnerable than others,…

Cryptography and Security · Computer Science 2021-03-02 Wenshuo Wang , Liang Cheng , Yang Zhang

Since the advent of AFL, the use of mutational, feedback directed, grey-box fuzzers has become critical in the automated detection of security vulnerabilities. A great deal of research currently goes into their optimisation, including…

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