English
Related papers

Related papers: Unsafe Impedance: Safe Languages and Safe by Desig…

200 papers

We introduce time-to-unsafe-sampling, a novel safety measure for generative models, defined as the number of generations required by a large language model (LLM) to trigger an unsafe (e.g., toxic) response. While providing a new dimension…

Machine Learning · Computer Science 2026-02-17 Hen Davidov , Shai Feldman , Gilad Freidkin , Yaniv Romano

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as…

Computation and Language · Computer Science 2025-06-06 Chengwu Liu , Ye Yuan , Yichun Yin , Yan Xu , Xin Xu , Zaoyu Chen , Yasheng Wang , Lifeng Shang , Qun Liu , Ming Zhang

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Artificial Intelligence · Computer Science 2026-02-18 Sanidhya Vijayvargiya , Aditya Bharat Soni , Xuhui Zhou , Zora Zhiruo Wang , Nouha Dziri , Graham Neubig , Maarten Sap

AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization,…

Cryptography and Security · Computer Science 2026-02-25 Genliang Zhu , Chu Wang , Ziyuan Wang , Zhida Li , Qiang Li

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Cryptography and Security · Computer Science 2025-09-10 Hongfei Xia , Hongru Wang , Zeming Liu , Qian Yu , Yuhang Guo , Haifeng Wang

Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or…

Cryptography and Security · Computer Science 2026-05-19 Isaac David , Arthur Gervais

We propose a new formal criterion for evaluating secure compilation schemes for unsafe languages, expressing end-to-end security guarantees for software components that may become compromised after encountering undefined behavior---for…

The damage caused by cybercrime makes the development of secure software inevitable. Although many tools and frameworks exist to support the development of secure software, statistics on cybercrime show no improvement in recent years. To…

Software Engineering · Computer Science 2025-12-09 Alex R. Mattukat , Timo Langstrof , Horst Lichter

Ensuring safe interactions in human-centric environments requires robots to understand and adhere to constraints recognized by humans as "common sense" (e.g., "moving a cup of water above a laptop is unsafe as the water may spill" or…

Robotics · Computer Science 2025-04-10 Lukas Brunke , Yanni Zhang , Ralf Römer , Jack Naimer , Nikola Staykov , Siqi Zhou , Angela P. Schoellig

The popularity of large language models (LLMs) continues to grow, and LLM-based assistants have become ubiquitous. Information security awareness (ISA) is an important yet underexplored area of LLM safety. ISA encompasses LLMs' security…

Cryptography and Security · Computer Science 2026-03-23 Ofir Cohen , Gil Ari Agmon , Asaf Shabtai , Rami Puzis

Large language models (LLMs) are being increasingly integrated into practical hardware and firmware development pipelines for code generation. Existing studies have primarily focused on evaluating the functional correctness of LLM-generated…

Cryptography and Security · Computer Science 2026-01-21 Qirui Chen , Jingxian Shuai , Shuangwu Chen , Shenghao Ye , Zijian Wen , Xufei Su , Jie Jin , Jiangming Li , Jun Chen , Xiaobin Tan , Jian Yang

In recent years, numerous incidents involving the leakage of website accounts and text passwords (referred to as passwords) have raised significant concerns regarding the potential exposure of personal information. These events underscore…

Cryptography and Security · Computer Science 2026-04-07 Abel C. H. Chen

Producing secure software is challenging. The poor usability of security APIs makes this even harder. Many recommendations have been proposed to support developers by improving the usability of cryptography libraries and APIs; rooted in…

Cryptography and Security · Computer Science 2021-05-06 Nikhil Patnaik , Andrew C. Dwyer , Joseph Hallett , Awais Rashid

Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and…

Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various…

Cryptography and Security · Computer Science 2025-07-16 Yiting Qu , Michael Backes , Yang Zhang

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Computation and Language · Computer Science 2024-01-25 Lingfeng Shen , Weiting Tan , Sihao Chen , Yunmo Chen , Jingyu Zhang , Haoran Xu , Boyuan Zheng , Philipp Koehn , Daniel Khashabi

Linguistically inclusive LLMs -- which maintain good performance regardless of the language with which they are prompted -- are necessary for the diffusion of AI benefits around the world. Multilingual jailbreaks that rely on language…

Computation and Language · Computer Science 2024-10-30 Artūrs Kanepajs , Vladimir Ivanov , Richard Moulange

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon -- a keylogger, a ransomware stub, an exploit that runs as written. This…

Cryptography and Security · Computer Science 2026-05-28 Richard J. Young , Gregory D. Moody

We present a benchmark suite of four datasets for evaluating the fairness of pre-trained language models and the techniques used to fine-tune them for downstream tasks. Our benchmarks cover four jurisdictions (European Council, USA,…

Computation and Language · Computer Science 2022-03-15 Ilias Chalkidis , Tommaso Pasini , Sheng Zhang , Letizia Tomada , Sebastian Felix Schwemer , Anders Søgaard

PowerShell is a command-line shell, supporting a scripting language. It is widely used in organizations for configuration management and task automation but is also increasingly used by cybercriminals for launching cyberattacks against…

Cryptography and Security · Computer Science 2019-09-20 Amir Rubin , Shay Kels , Danny Hendler