English
Related papers

Related papers: CaMeLs Can Use Computers Too: System-level Securit…

200 papers

AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…

Computers and Society · Computer Science 2025-12-02 K. J. Kevin Feng , Tae Soo Kim , Rock Yuren Pang , Faria Huq , Tal August , Amy X. Zhang

European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing but by reasoning capacity: enterprise SIEMs cover only a fraction of MITRE ATT&CK…

The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge…

Cryptography and Security · Computer Science 2025-12-09 Mehrab Hosain , Sabbir Alom Shuvo , Matthew Ogbe , Md Shah Jalal Mazumder , Yead Rahman , Md Azizul Hakim , Anukul Pandey

Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…

Cryptography and Security · Computer Science 2026-03-17 Simone Aonzo , Merve Sahin , Aurélien Francillon , Daniele Perito

Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding…

Cryptography and Security · Computer Science 2026-04-21 Shutong Jin , Ruiyi Guo , Ray C. C. Cheung

Defense mechanisms against network-level attacks are commonly based on the use of cryptographic techniques, such as message authentication codes that provide data integrity guarantees. However, such mechanisms require significant resources,…

Software Engineering · Computer Science 2018-11-09 Vuk Lesi , Ilija Jovanov , Miroslav Pajic

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

Cryptography and Security · Computer Science 2025-12-30 Toqeer Ali Syed , Mishal Ateeq Almutairi , Mahmoud Abdel Moaty

Autonomous AI agents executing multi-step tool sequences face semantic attacks that manifest in behavioral traces rather than isolated prompts. A critical challenge is cross-attack generalization: can detectors trained on known attack…

Cryptography and Security · Computer Science 2026-01-06 Vignesh Iyer

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

Cryptography and Security · Computer Science 2025-09-10 Haitao Hu , Peng Chen , Yanpeng Zhao , Yuqi Chen

When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…

Human-Computer Interaction · Computer Science 2022-11-09 Travis Mandel , Jahnu Best , Randall H. Tanaka , Hiram Temple , Chansen Haili , Kayla Schlectinger , Roy Szeto

We introduce the Context Compliance Attack (CCA), a novel, optimization-free method for bypassing AI safety mechanisms. Unlike current approaches -- which rely on complex prompt engineering and computationally intensive optimization -- CCA…

Cryptography and Security · Computer Science 2025-03-10 Mark Russinovich , Ahmed Salem

Computer Using Agents (CUAs) are increasingly equipped with external tools, enabling them to perform complex and realistic tasks. For CUAs to operate effectively, application selection, which refers to deciding which application to use…

Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversarial attacks, and reduce the number of parameters without…

Software Engineering · Computer Science 2024-12-18 Mykhailo Klymenko , Thong Hoang , Xiwei Xu , Zhenchang Xing , Muhammad Usman , Qinghua Lu , Liming Zhu

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

As AI models become more embedded in critical sectors like finance, healthcare, and the military, their inscrutable behavior poses ever-greater risks to society. To mitigate this risk, we propose Guillotine, a hypervisor architecture for…

Cryptography and Security · Computer Science 2025-04-23 James Mickens , Sarah Radway , Ravi Netravali

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

Artificial Intelligence · Computer Science 2026-04-21 Hailin Liu , Eugene Ilyushin , Jie Ni , Min Zhu

We present ideas about creating a next generation Intrusion Detection System based on the latest immunological theories. The central challenge with computer security is determining the difference between normal and potentially harmful…

Neural and Evolutionary Computing · Computer Science 2010-07-05 Uwe Aickelin , Peter Bentley , Steve Cayzer , Kim Jungwon , Julie McLeod

Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…

Artificial Intelligence · Computer Science 2025-01-29 Zeki Doruk Erden , Boi Faltings

As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untrusted AI agents by monitoring their actions and intervening or…

Artificial Intelligence · Computer Science 2025-11-06 Jon Kutasov , Chloe Loughridge , Yuqi Sun , Henry Sleight , Buck Shlegeris , Tyler Tracy , Joe Benton
‹ Prev 1 8 9 10 Next ›