English
Related papers

Related papers: Measuring AI Agents' Progress on Multi-Step Cyber …

200 papers

Despite extensive investment in artificial intelligence, 95% of enterprises report no measurable profit impact from AI deployments (MIT, 2025). In this theoretical paper, we argue that this gap reflects paradigmatic lock-in that channels AI…

Computers and Society · Computer Science 2025-09-15 Diana A. Wolfe , Alice Choe , Fergus Kidd

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…

Artificial Intelligence · Computer Science 2026-02-24 Stephan Rabanser , Sayash Kapoor , Peter Kirgis , Kangheng Liu , Saiteja Utpala , Arvind Narayanan

This report introduces the concept of "Highly Autonomous Cyber-Capable Agents" (HACCAs), AI systems capable of autonomously conducting multi-stage cyber campaigns at a level comparable to today's top criminal hacking groups or…

Computers and Society · Computer Science 2026-03-13 Jam Kraprayoon , Shaun Ee , Brianna Rosen , Yohan Matthew , Aditya Singh , Christopher Covino , Asher Brass Gershovich

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies,…

Cryptography and Security · Computer Science 2026-02-13 Aashish Kolluri , Rishi Sharma , Manuel Costa , Boris Köpf , Tobias Nießen , Mark Russinovich , Shruti Tople , Santiago Zanella-Béguelin

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Computation and Language · Computer Science 2025-07-17 Joe Needham , Giles Edkins , Govind Pimpale , Henning Bartsch , Marius Hobbhahn

Autonomous AI agents increasingly issue side-effect-bearing actions: database mutations, refunds, payments, external commitments. We propose the Actuarial Action Interface (AAI), a deterministic runtime contract that prices each such action…

Artificial Intelligence · Computer Science 2026-05-26 Hao-Hsuan Chen

Frontier artificial intelligence (AI) systems could pose increasing risks to public safety and security. But what level of risk is acceptable? One increasingly popular approach is to define capability thresholds, which describe AI…

Computers and Society · Computer Science 2024-06-24 Leonie Koessler , Jonas Schuett , Markus Anderljung

Today, human security analysts collapse under the sheer volume of alerts they have to triage during investigations. The inability to cope with this load, coupled with a high false positive rate of alerts, creates alert fatigue. This results…

Cryptography and Security · Computer Science 2021-03-29 Florian Wilkens , Felix Ortmann , Steffen Haas , Matthias Vallentin , Mathias Fischer

AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…

Artificial Intelligence · Computer Science 2026-05-08 Jonas Wiedermann-Möller , Leonard Dung , Maksym Andriushchenko

We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…

Artificial Intelligence · Computer Science 2024-12-23 Paolo Bova , Alessandro Di Stefano , The Anh Han

AI research agents accelerate ML research by automating hypothesis generation, experimentation, and empirical refinement. Existing agent strategies range from greedy hill-climbing to tree search and evolutionary optimization, yet which…

The plethora of complex artificial intelligence (AI) algorithms and available high performance computing (HPC) power stimulates the expeditious development of AI components with heterogeneous designs. Consequently, the need for cross-stack…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-03-16 Zhixiang Ren , Yongheng Liu , Tianhui Shi , Lei Xie , Yue Zhou , Jidong Zhai , Youhui Zhang , Yunquan Zhang , Wenguang Chen

Three factors drive the advance of AI: algorithmic innovation, data, and the amount of compute available for training. Algorithmic progress has traditionally been more difficult to quantify than compute and data. In this work, we argue that…

Machine Learning · Computer Science 2020-05-12 Danny Hernandez , Tom B. Brown

This work evaluates the performance of Cyber Threat Intelligence (CTI) extraction methods in identifying attack techniques from threat reports available on the web using the MITRE ATT&CK framework. We analyse four configurations utilising…

Cryptography and Security · Computer Science 2025-05-07 Hoang Cuong Nguyen , Shahroz Tariq , Mohan Baruwal Chhetri , Bao Quoc Vo

AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show…

Cryptography and Security · Computer Science 2026-03-24 Rishika Bhagwatkar , Kevin Kasa , Abhay Puri , Gabriel Huang , Irina Rish , Graham W. Taylor , Krishnamurthy Dj Dvijotham , Alexandre Lacoste

As Language Models (LMs) increasingly operate as autonomous agents, accurately forecasting their capabilities becomes crucial for societal preparedness. We evaluate six forecasting methods that predict downstream capabilities of LM agents.…

Computation and Language · Computer Science 2025-03-04 Govind Pimpale , Axel Højmark , Jérémy Scheurer , Marius Hobbhahn

Understanding the attack patterns associated with a cyberattack is crucial for comprehending the attacker's behaviors and implementing the right mitigation measures. However, majority of the information regarding new attacks is typically…

Machine Learning · Computer Science 2024-12-02 Weiqiu You , Youngja Park

Background: Large-scale biological jobs on high-performance computing systems require manual intervention if one or more computing cores on which they execute fail. This places not only a cost on the maintenance of the job, but also a cost…

Distributed, Parallel, and Cluster Computing · Computer Science 2014-03-04 Blesson Varghese , Gerard McKee , Vassil Alexandrov

Despite the scale of capital being deployed toward AI initiatives, no empirical framework currently exists for benchmarking where a firm stands relative to competitors in AI readiness and deployment, or for translating that position into…

General Economics · Economics 2026-03-17 Dean Barr
‹ Prev 1 3 4 5 6 7 10 Next ›