English
Related papers

Related papers: Beyond Input Guardrails: Reconstructing Cross-Agen…

200 papers

Insider Attack Detection in commercial networks is a critical problem that does not have any good solutions at this current time. The problem is challenging due to the lack of visibility into live networks and a lack of a standard feature…

Cryptography and Security · Computer Science 2020-10-30 Yash Samtani , Jesse Elwell

This paper proposes a query-level meta-agent named FlowReasoner to automate the design of query-level multi-agent systems, i.e., one system per user query. Our core idea is to incentivize a reasoning-based meta-agent via external execution…

Artificial Intelligence · Computer Science 2025-04-22 Hongcheng Gao , Yue Liu , Yufei He , Longxu Dou , Chao Du , Zhijie Deng , Bryan Hooi , Min Lin , Tianyu Pang

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these…

Cryptography and Security · Computer Science 2026-05-25 Yuanbo Zhou , Changjia Zhu , Junyu Wang , Xu He , Yan Zhai , Kun Sun , Mingkui Wei , Junjie Xiong

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK…

Cryptography and Security · Computer Science 2026-02-12 Peiran Wang , Xinfeng Li , Chong Xiang , Jinghuai Zhang , Ying Li , Lixia Zhang , Xiaofeng Wang , Yuan Tian

As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design…

Computation and Language · Computer Science 2025-11-10 Gauri Kholkar , Ratinder Ahuja

Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…

Machine Learning · Computer Science 2026-03-27 Mohammad Meymani , Roozbeh Razavi-Far

Distributed training of large deep-learning models often leads to failures, so checkpointing is commonly employed for recovery. State-of-the-art studies focus on frequent checkpointing for fast recovery from failures. However, it generates…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-25 Chenxuan Yao , Yuchong Hu , Feifan Liu , Zhengyu Liu , Lin Wang , Mingqi Li , Dan Feng

Subliminal prompting is a phenomenon in which language models are biased towards certain concepts or traits through prompting with semantically unrelated tokens. While prior work has examined subliminal prompting in user-LLM interactions,…

Multiagent Systems · Computer Science 2026-03-03 Moritz Weckbecker , Jonas Müller , Ben Hagag , Michael Mulet

Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation,…

Artificial Intelligence · Computer Science 2025-12-22 Ali Eslami , Jiangbo Yu

We present SEIF, a methodology that combines static analysis with symbolic execution to verify and explicate information flow paths in a hardware design. SEIF begins with a statically built model of the information flow through a design and…

Cryptography and Security · Computer Science 2023-08-03 Kaki Ryan , Matthew Gregoire , Cynthia Sturton

Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typically classify any input with instruction as malicious,…

Cryptography and Security · Computer Science 2026-02-24 Yuqi Jia , Ruiqi Wang , Xilong Wang , Chong Xiang , Neil Gong

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Cryptography and Security · Computer Science 2025-06-12 Li Changjiang , Liang Jiacheng , Cao Bochuan , Chen Jinghui , Wang Ting

6G services are evolving toward goal-oriented and AI-native communication, which are expected to deliver transformative societal benefits across various industries and promote energy sustainability. Yet today's networking architectures,…

Networking and Internet Architecture · Computer Science 2026-03-26 Shutong Chen , Qi Liao , Adnan Aijaz , Yansha Deng

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

Artificial Intelligence · Computer Science 2026-04-06 Yunhao Feng , Yifan Ding , Yingshui Tan , Xingjun Ma , Yige Li , Yutao Wu , Yifeng Gao , Kun Zhai , Yanming Guo

Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data. Existing methods collect privacy-constrained API logs or…

Computation and Language · Computer Science 2026-02-11 Zexu Sun , Bokai Ji , Hengyi Cai , Shuaiqiang Wang , Lei Wang , Guangxia Li , Xu Chen

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…

Machine Learning · Computer Science 2025-04-15 Aryan Bhatt , Cody Rushing , Adam Kaufman , Tyler Tracy , Vasil Georgiev , David Matolcsi , Akbir Khan , Buck Shlegeris

This paper investigates a flow- and path-sensitive static information flow analysis. Compared with security type systems with fixed labels, it has been shown that flow-sensitive type systems accept more secure programs. We show that an…

Programming Languages · Computer Science 2017-06-22 Peixuan Li , Danfeng Zhang

Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static…

Cryptography and Security · Computer Science 2026-03-20 Haochen Zhao , Shaoyang Cui

Code-capable large language model (LLM) agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass ("jailbreak") attacks beyond text-only settings.…

Cryptography and Security · Computer Science 2025-10-03 Shoumik Saha , Jifan Chen , Sam Mayers , Sanjay Krishna Gouda , Zijian Wang , Varun Kumar

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

Artificial Intelligence · Computer Science 2025-04-02 Seyoung Song