English
Related papers

Related papers: Detecting Safety Violations Across Many Agent Trac…

200 papers

Advanced persistent threats (APT) are stealthy cyber-attacks that are aimed at stealing valuable information from target organizations and tend to extend in time. Blocking all APTs is impossible, security experts caution, hence the…

Cryptography and Security · Computer Science 2021-05-24 Sidahmed Benabderrahmane , Ghita Berrada , James Cheney , Petko Valtchev

As AI systems are increasingly deployed in autonomous agentic settings at scale, it is important to ensure the actions they take are safe and aligned with user intent. Monitoring agent actions is a key safety mechanism, yet reliable…

Artificial Intelligence · Computer Science 2026-05-19 Eugene Koran , Yejun Yun , Samantha Tetef , Benjamin Arnav , Pablo Bernabeu-Pérez

Memory leaks are prevalent in various real-world software projects, thereby leading to serious attacks like denial-of-service. Though prior methods for detecting memory leaks made significant advance, they often suffer from low accuracy and…

Cryptography and Security · Computer Science 2025-04-08 Hongliang Liang , Luming Yin , Guohao Wu , Yuxiang Li , Qiuping Yi , Lei Wang

As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…

Computers and Society · Computer Science 2025-08-21 Carson Ezell , Xavier Roberts-Gaal , Alan Chan

The aggressive performance optimizations in modern microprocessors can result in security vulnerabilities. For example, timing-based attacks in processor caches can steal secret keys or break randomization. So far, finding cache-timing…

Cryptography and Security · Computer Science 2023-02-07 Mulong Luo , Wenjie Xiong , Geunbae Lee , Yueying Li , Xiaomeng Yang , Amy Zhang , Yuandong Tian , Hsien-Hsin S. Lee , G. Edward Suh

Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural-language reasoning, nondeterministic outputs, and intricate…

Multiagent Systems · Computer Science 2026-04-27 Mengzhuo Chen , Junjie Wang , Fangwen Mu , Yawen Wang , Zhe Liu , Huanxiang Feng , Qing Wang

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Cryptography and Security · Computer Science 2026-04-08 Zenghao Duan , Yuxin Tian , Zhiyi Yin , Liang Pang , Jingcheng Deng , Zihao Wei , Shicheng Xu , Yuyao Ge , Xueqi Cheng

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Computation and Language · Computer Science 2026-05-22 Asaf Yehudai , Lilach Eden , Michal Shmueli-Scheuer

Sensitive information leakage in code repositories has emerged as a critical security challenge. Traditional detection methods that rely on regular expressions, fingerprint features, and high-entropy calculations often suffer from high…

Cryptography and Security · Computer Science 2025-12-10 Bin Wang , Hui Li , Liyang Zhang , Qijia Zhuang , Ao Yang , Dong Zhang , Xijun Luo , Bing Lin

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…

Artificial Intelligence · Computer Science 2026-05-26 Jingwei Sun , Jianing Zhu , Yuanyi Li , Tongliang Liu , Xia HU , Bo Han

Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent…

Artificial Intelligence · Computer Science 2026-02-13 Sina Tayebati , Divake Kumar , Nastaran Darabi , Davide Ettori , Ranganath Krishnan , Amit Ranjan Trivedi

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…

Artificial Intelligence · Computer Science 2025-03-11 Dany Moshkovich , Hadar Mulian , Sergey Zeltyn , Natti Eder , Inna Skarbovsky , Roy Abitbol

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Cryptography and Security · Computer Science 2026-04-07 Khanh Linh Nguyen , Hoa Nghiem , Tu Tran

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…

Cryptography and Security · Computer Science 2026-05-20 Elle Najt , Colin Toft , Tyler Tracy , Fabien Roger , Joe Benton

Security practitioners face growing challenges in exploit assessment, as public vulnerability repositories are increasingly populated with inconsistent and low-quality exploit artifacts. Existing scoring systems, such as CVSS and EPSS,…

Cryptography and Security · Computer Science 2025-09-23 Xiangmin Shen , Wenyuan Cheng , Yan Chen , Zhenyuan Li , Yuqiao Gu , Lingzhi Wang , Wencheng Zhao , Dawei Sun , Jiashui Wang

In active visual tracking, it is notoriously difficult when distracting objects appear, as distractors often mislead the tracker by occluding the target or bringing a confusing appearance. To address this issue, we propose a mixed…

Computer Vision and Pattern Recognition · Computer Science 2021-06-21 Fangwei Zhong , Peng Sun , Wenhan Luo , Tingyun Yan , Yizhou Wang

Multi-implementation systems are increasingly audited against natural-language specifications. Differential testing scales well when implementations disagree, but it provides little signal when all implementations converge on the same…

Cryptography and Security · Computer Science 2026-02-11 Masato Kamba , Akiyoshi Sannai

Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…

Software Engineering · Computer Science 2026-02-12 Adam AlSayyad , Kelvin Yuxiang Huang , Richik Pal

Advanced Persistent Threats (APTs) are sophisticated multi-step attacks, planned and executed by skilled adversaries targeting modern government and enterprise networks. Intrusion Detection Systems (IDSs) and User and Entity Behavior…

Cryptography and Security · Computer Science 2021-01-08 Hazem M. Soliman , Geoff Salmon , Dušan Sovilj , Mohan Rao

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject…

Cryptography and Security · Computer Science 2026-05-12 Zhichao Liu , Wenbo Pan , Haining Yu , Ge Gao , Tianqing Zhu , Xiaohua Jia