English
Related papers

Related papers: Alignment Contracts for Agentic Security Systems

200 papers

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun

Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a…

Operating Systems · Computer Science 2025-10-21 Yusheng Zheng , Yanpeng Hu , Tong Yu , Andi Quinn

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Cryptography and Security · Computer Science 2026-04-30 Matteo Leonesi , Francesco Belardinelli , Flavio Corradini , Marco Piangerelli

AI agent protocols -- including MCP, A2A, ANP, and ACP -- enable autonomous agents to discover capabilities, delegate tasks, and compose services across trust boundaries. Despite massive deployment (MCP alone has 97M+ monthly SDK…

Cryptography and Security · Computer Science 2026-03-26 Shenghan Zheng , Qifan Zhang

Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…

Software Engineering · Computer Science 2026-05-14 Jacqueline L. Mitchell , Chao Wang

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

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Machine Learning · Computer Science 2025-05-30 Zhen Xiang , Linzhi Zheng , Yanjie Li , Junyuan Hong , Qinbin Li , Han Xie , Jiawei Zhang , Zidi Xiong , Chulin Xie , Carl Yang , Dawn Song , Bo Li

The shift from monolithic LLMs to distributed multi-agent architectures demands new frameworks for verifying and securing autonomous coordination. Unlike traditional multi-agent systems focused on cooperative state alignment, modern LLM…

Multiagent Systems · Computer Science 2026-03-06 Muhammad Umar Javed

This paper studies the synthesis of control policies for an agent that has to satisfy a temporal logic specification in a partially observable environment, in the presence of an adversary. The interaction of the agent (defender) with the…

Systems and Control · Electrical Eng. & Systems 2020-11-09 Bhaskar Ramasubramanian , Luyao Niu , Andrew Clark , Linda Bushnell , Radha Poovendran

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…

Cryptography and Security · Computer Science 2026-05-15 Haomin Zhuang , Hanwen Xing , Yujun Zhou , Yuchen Ma , Yue Huang , Yili Shen , Yufei Han , Xiangliang Zhang

As LLM-based agents grow more autonomous and multi-modal, ensuring they remain controllable, auditable, and faithful to deployer intent becomes critical. Prior benchmarks measured the propensity for misaligned behavior and showed that agent…

Multiagent Systems · Computer Science 2025-12-22 Abhivansh Gupta

The autonomous AI agents using large language models can create undeniable values in all span of the society but they face security threats from adversaries that warrants immediate protective solutions because trust and safety issues arise.…

Cryptography and Security · Computer Science 2025-06-13 Saikat Barua , Mostafizur Rahman , Md Jafor Sadek , Rafiul Islam , Shehenaz Khaled , Ahmedul Kabir

LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership, and unauthorized reuse difficult to establish from observed…

Cryptography and Security · Computer Science 2026-05-13 Hyeseon An , Shinwoo Park , Dongsu Kim , Yo-Sub Han

Agentic systems involved in high-stake decision-making under adversarial pressure need formal guarantees not offered by existing approaches. Motivated by the operational needs of security operations centers (SOCs) that must configure…

Artificial Intelligence · Computer Science 2026-05-06 Kerri Prinos , Lilianne Brush , Cameron Denton , Zhanqi Wang , Joshua Knox , Snehal Antani , Anton Foltz , Amy Villaseñor

The Contract Net Protocol (1980) introduced coordination through contracts in multi-agent systems. Modern agent protocols standardize connectivity and interoperability; yet, none provide formal, resource governance-normative mechanisms to…

Multiagent Systems · Computer Science 2026-03-26 Qing Ye , Jing Tan

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Artificial Intelligence · Computer Science 2026-02-17 Igor Santos-Grueiro

Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…

Logic in Computer Science · Computer Science 2026-03-24 Melwin Xavier , Vaisakh M A , Melveena Jolly , Midhun Xavier

The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks…