English
Related papers

Related papers: ORFuzz: Fuzzing the "Other Side" of LLM Safety -- …

200 papers

Large Language Models (LLMs) require careful safety alignment to prevent malicious outputs. While significant research focuses on mitigating harmful content generation, the enhanced safety often come with the side effect of over-refusal,…

Computation and Language · Computer Science 2025-06-17 Justin Cui , Wei-Lin Chiang , Ion Stoica , Cho-Jui Hsieh

Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard…

Cryptography and Security · Computer Science 2025-11-25 Junbo Zhang , Ran Chen , Qianli Zhou , Xinyang Deng , Wen Jiang

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overrefusal. Overrefusal typically stems from over-conservative…

Artificial Intelligence · Computer Science 2025-09-18 Licheng Pan , Yongqi Tong , Xin Zhang , Xiaolu Zhang , Jun Zhou , Zhixuan Chu

Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user…

Artificial Intelligence · Computer Science 2026-01-21 Xiaorui Wu , Fei Li , Xiaofeng Mao , Xin Zhang , Li Zheng , Yuxiang Peng , Chong Teng , Donghong Ji , Zhuang Li

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

Large Language Models (LLMs) have gained widespread use in various applications due to their powerful capability to generate human-like text. However, prompt injection attacks, which involve overwriting a model's original instructions with…

Cryptography and Security · Computer Science 2025-04-07 Jiahao Yu , Yangguang Shao , Hanwen Miao , Junzheng Shi

Fuzz testing is a crucial component of software security assessment, yet its effectiveness heavily relies on valid fuzz drivers and diverse seed inputs. Recent advancements in Large Language Models (LLMs) offer transformative potential for…

Software Engineering · Computer Science 2025-03-04 Yiran Cheng , Hong Jin Kang , Lwin Khin Shar , Chaopeng Dong , Zhiqiang Shi , Shichao Lv , Limin Sun

Large Language Model (LLM) Agents leverage the advanced reasoning capabilities of LLMs in real-world applications. To interface with an environment, these agents often rely on tools, such as web search or database APIs. As the agent…

Artificial Intelligence · Computer Science 2025-03-12 Ivan Milev , Mislav Balunović , Maximilian Baader , Martin Vechev

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

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

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in \emph{over-refusal} of benign queries or \emph{unsafe compliance} with harmful ones. While existing…

Artificial Intelligence · Computer Science 2026-01-27 Zhihao Zhang , Liting Huang , Guanghao Wu , Preslav Nakov , Heng Ji , Usman Naseem

Fuzzing has shown great success in evaluating the robustness of intelligent natural language processing (NLP) software. As large language model (LLM)-based NLP software is widely deployed in critical industries, existing methods still face…

Software Engineering · Computer Science 2025-09-23 Mingxuan Xiao , Yan Xiao , Shunhui Ji , Jiahe Tu , Pengcheng Zhang

Safety alignment in large language models (LLMs) induces over-refusals -- where LLMs decline benign requests due to aggressive safety filters. We analyze this phenomenon in retrieval-augmented generation (RAG), where both the query intent…

Computation and Language · Computer Science 2025-10-14 Utsav Maskey , Mark Dras , Usman Naseem

In the modern era where software plays a pivotal role, software security and vulnerability analysis are essential for secure software development. Fuzzing test, as an efficient and traditional software testing method, has been widely…

Software Engineering · Computer Science 2025-05-20 Linghan Huang , Peizhou Zhao , Huaming Chen , Lei Ma

Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant…

Cryptography and Security · Computer Science 2026-05-05 Mario Rodríguez Béjar , B. Romera-Paredes , Jose L. Hernández-Ramos

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

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars. It is of significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always…

Software Engineering · Computer Science 2018-08-29 Jianmin Guo , Yu Jiang , Yue Zhao , Quan Chen , Jiaguang Sun

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Computation and Language · Computer Science 2025-07-16 Zhehao Zhang , Weijie Xu , Fanyou Wu , Chandan K. Reddy

The rapid development of large language models (LLMs) has revolutionized software testing, particularly fuzz testing, by automating the generation of diverse and effective test inputs. This advancement holds great promise for improving…

Software Engineering · Computer Science 2025-10-14 Linghan Huang , Peizhou Zhao , Huaming Chen

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
‹ Prev 1 2 3 10 Next ›