English
Related papers

Related papers: The Persistent Vulnerability of Aligned AI Systems

200 papers

Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every…

Cryptography and Security · Computer Science 2026-05-11 Christopher Koch

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…

Cryptography and Security · Computer Science 2026-03-19 Saikat Maiti

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…

Artificial Intelligence · Computer Science 2025-05-26 Marie Davidsen Buhl , Jacob Pfau , Benjamin Hilton , Geoffrey Irving

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Machine Learning · Computer Science 2025-10-29 Csaba Dékány , Stefan Balauca , Robin Staab , Dimitar I. Dimitrov , Martin Vechev

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Cryptography and Security · Computer Science 2026-05-25 Xueyi Li , Zhuoneng Zhou , Zitao Liu , Yongdong Wu

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Cryptography and Security · Computer Science 2026-04-28 Richard Joseph Mitchell

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

Cryptography and Security · Computer Science 2026-01-12 Sahaya Jestus Lazer , Kshitiz Aryal , Maanak Gupta , Elisa Bertino

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, especially as agentic coding frameworks increase the rate of code production. Over the last decade, a…

Software Engineering · Computer Science 2026-05-11 Dan Ristea , Shae McFadden , Ezzeldin Shereen , Madeleine Dwyer , Sanyam Vyas , Chris Hicks , Vasilios Mavroudis

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…

Machine Learning · Computer Science 2023-11-07 Raphaël Millière

In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools, such as web browsers, compilers, and more. However, despite their popularity, agentic AI…

Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Yanyun Wang , Qingqing Ye , Li Liu , Zi Liang , Haibo Hu

Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…

Cryptography and Security · Computer Science 2026-04-20 Xuwei Ding , Skylar Zhai , Linxin Song , Jiate Li , Taiwei Shi , Nicholas Meade , Siva Reddy , Jian Kang , Jieyu Zhao

Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials remains unstudied. This work presents the first large-scale empirical measurement of LLM…

Cryptography and Security · Computer Science 2026-05-29 Galip Tolga Erdem

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Cryptography and Security · Computer Science 2026-03-03 Zhihang Deng , Jiaping Gui , Weinan Zhang

When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers…

Cryptography and Security · Computer Science 2025-08-15 Pallavi Zambare , Venkata Nikhil Thanikella , Ying Liu

Autonomous agents are increasingly deployed in both offensive and defensive cyber operations, creating high-speed, closed-loop interactions in critical infrastructure environments. Advanced Persistent Threat (APT) actors exploit "Living off…

Cryptography and Security · Computer Science 2026-04-07 Yiyao Zhang , Diksha Goel , Hussain Ahmad