English
Related papers

Related papers: Large Empirical Case Study: Go-Explore adapted for…

200 papers

Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry,…

Cryptography and Security · Computer Science 2025-10-28 Pavlos Ntais

The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to…

Cryptography and Security · Computer Science 2026-01-13 Xin Wang , Yunhao Chen , Juncheng Li , Yixu Wang , Yang Yao , Tianle Gu , Jie Li , Yan Teng , Yingchun Wang , Xia Hu

Can large language model agents discover hidden safety objectives through experience alone? We introduce EPO-Safe (Experiential Prompt Optimization for Safe Agents), a framework where an LLM iteratively generates action plans, receives…

Artificial Intelligence · Computer Science 2026-04-28 Víctor Gallego

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Cryptography and Security · Computer Science 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz

Text-to-image (T2I) models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teaming is vital, yet white-box approaches are limited by their…

Machine Learning · Computer Science 2025-05-28 Yichuan Cao , Yibo Miao , Xiao-Shan Gao , Yinpeng Dong

Penetration testing (PT) is an efficient network testing and vulnerability mining tool by simulating a hacker's attack for valuable information applied in some areas. Compared with manual PT, intelligent PT has become a dominating…

Cryptography and Security · Computer Science 2022-04-06 Jinyin Chen , Shulong Hu , Haibin Zheng , Changyou Xing , Guomin Zhang

Safe exploration aims at addressing the limitations of Reinforcement Learning (RL) in safety-critical scenarios, where failures during trial-and-error learning may incur high costs. Several methods exist to incorporate external knowledge or…

Machine Learning · Computer Science 2023-07-13 Xiaotong Ji , Antonio Filieri

Efforts to ensure the safety of large language models (LLMs) include safety fine-tuning, evaluation, and red teaming. However, despite the widespread use of the Retrieval-Augmented Generation (RAG) framework, AI safety work focuses on…

Computation and Language · Computer Science 2025-04-28 Bang An , Shiyue Zhang , Mark Dredze

Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, limiting their ability to adapt to dynamic defenses and…

Cryptography and Security · Computer Science 2025-01-06 Yanjiang Liu , Shuhen Zhou , Yaojie Lu , Huijia Zhu , Weiqiang Wang , Hongyu Lin , Ben He , Xianpei Han , Le Sun

Ensuring agent behaviors in distributed open multi-agent systems remains challenging, especially as populations grow and unaligned agents may exist. We show that a single aligned agent can propagate cooperative behaviors to untrained agents…

Multiagent Systems · Computer Science 2026-05-28 Nicole Hsing , Asuka Yuxi Zheng , Yi Zhao , Haoqin Tu , Jen-Tse Huang

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study of a multi-agent autonomous testing system evaluated using anonymized execution data from a…

Software Engineering · Computer Science 2026-05-05 Hyukjoo Lee

Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment under distribution shift, using diabetes management as a…

Machine Learning · Computer Science 2026-05-26 Minjae Kwon , Josephine Lamp , Lu Feng

The field of software security testing, more specifically penetration testing, is an activity that requires high levels of expertise and involves many manual testing and analysis steps. This paper explores the potential usage of…

Computation and Language · Computer Science 2023-10-19 Andreas Happe , Jürgen Cito

Software Engineering (SE) experiments are traditionally analyzed with statistical tests (e.g., t-tests, ANOVAs, etc.) that assume equally spread data across treatments (i.e., the homogeneity of variances assumption). Differences across…

Software Engineering · Computer Science 2018-09-06 Adrian Santos , Markku Oivo , Natalia Juristo

Equipped with various tools and knowledge, GPTs, one kind of customized AI agents based on OpenAI's large language models, have illustrated great potential in many fields, such as writing, research, and programming. Today, the number of…

Cryptography and Security · Computer Science 2025-12-02 Tong Wu , Weibin Wu , Zibin Zheng

In this paper we show that reporting a single performance score is insufficient to compare non-deterministic approaches. We demonstrate for common sequence tagging tasks that the seed value for the random number generator can result in…

Computation and Language · Computer Science 2017-08-01 Nils Reimers , Iryna Gurevych

The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the…

Cryptography and Security · Computer Science 2025-11-25 Tom Perel

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

Multiagent Systems · Computer Science 2025-08-11 Alistair Reid , Simon O'Callaghan , Liam Carroll , Tiberio Caetano

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

Machine Learning · Computer Science 2026-05-06 Kunvar Thaman