Results for “Agent”

arXiv (research papers) Minghui Pan SI

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions. Yet LLMs often become substantially less safe when deployed as agents, and the source of this degradation remains poorly understood. In this paper, we identify schema-formatted tool specifications as a primary source of agent safety degradation and show, through white-box representation analysis, that…

Read at arXiv (research papers)

arXiv (research papers) Mingxiao Liu Hangzhou Dianzi University SI

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain environmental noise beyond user control. In this paper, we investigate concurrent audio prompt injection attacks targeting multimodal agents. Distinct from traditional acoustic attacks on…

Read at arXiv (research papers)

Journal articles (OpenAlex) Thanh Sơn Lê, Huu Sy Le, Nguyen Tan Viet Tuyen et al. · Advanced Robotics Gadgets

Graph convolutional reinforcement learning for multi-agent coordination in smart home environments: an intelligent framework for elderly care assistance

The rapid aging of global populations presents unprecedented challenges for elderly care systems, particularly for individuals living independently who require assistance with daily activities. This paper presents a novel Graph Convolutional Reinforcement Learning (GCRL) framework for multi-agent coordination in smart home environments. Our approach addresses five fundamental gaps in existing systems: unified relational representations for heterogeneous agents and objects…

Read at Journal articles (OpenAlex)

arXiv (research papers) Eric Wallace SI

GPT-Red: Automated Red Teaming via Self-Play at Scale

We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this end, we use it to adversarially train GPT-5.6, our most robust model to prompt injections to date. To create GPT-Red, we design a scalable self-play algorithm where the model is tasked with attacking a diverse population of…

Read at arXiv (research papers)

arXiv (research papers) Haowen Dai SI

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We…

Read at arXiv (research papers)

arXiv (research papers) Arseny Kravchenko SI

APPA: Recoverable Information-Flow Control for Real-World LLM Agents

LLM agents deployed in practical workflows routinely mix private context, untrusted tool and web outputs, and external side effects. While information-flow control (IFC) provides structural defenses against prompt injection, data exfiltration, and confused-deputy attacks, conventional IFC relies on monotone taint tracking that either over-blocks benign operations or permanently strands downstream execution once an agent ingests unvetted data. We present APPA (Agentic…

Read at arXiv (research papers)

arXiv (research papers) Mohan Manivannan SI

Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident reconstructing context the logs already contain. We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language model agent that compresses the…

Read at arXiv (research papers)

arXiv (research papers) Zhaoxi Zhang SI

Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents

Long-lived AI agents increasingly evolve after deployment by retaining experience, acquiring skills and tools, revising workflows, delegating work, and moving across task phases. This improves adaptation but creates a distinct authorization problem. Tool-enabled agents can turn model errors and prompt injections into consequential external actions; when evolution occurs under a live grant, the subject exercising that authority or the context in which it acts may no longer…

Read at arXiv (research papers)

Berkeley AI Research blog SI

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

Overview of ABBEL compared to traditional recursive summarization. Beliefs replace the full interaction history as the agent’s working context, and belief grading improves performance by supervising the contents of each belief state.. As task horizons grow, LLM contexts can’t scale forever. Self-summarization enables concise, interpretable contexts, but at a significant performance cost, especially for human assistance domains where high quality data is scarce, e.g…

Read at Berkeley AI Research blog

arXiv (research papers) Vincent Siu SI

Agent Security Needs Redefinition through a Holistic Framework

Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user data'' might be a routine administrative request or a prompt injection attacking production systems, and the…

Read at arXiv (research papers)

arXiv (research papers) Yedidel Louck SI

Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense

Agentic commerce platforms let AI agents autonomously discover services, move payments, and wield user credentials on their users' behalf, and they already handle real money. Their security has so far been studied almost entirely at the level of the AI model, through prompt injection and misalignment. We show that the more consequential risks lie one layer down, in the protocol between agents and commerce services. There, vulnerabilities are structural : exploitation is…

Read at arXiv (research papers)

Journal of Democracy Alex Gladstein Geopolitics

How AI Agents Are Empowering Human-Rights Defenders

AI isn’t just a weapon for dictators and tyrants. It can also be a tool for liberty. Human-rights activists are learning how to harness its power and level the playing field for good. Source

Read at Journal of Democracy

arXiv (research papers) Or Zion Eliav SI

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract: what they are, how they are used, and which agent weaknesses they exploit to give adversaries leverage in indirect prompt injection attacks. We instantiate these insights in…

Read at arXiv (research papers)

arXiv (research papers) Zhanhao Hu SI

Twin Agent: Context Residual Compression for Privilege Separated Agents

Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and careful control of information flow, but often degrade utility and require extensive task-specific engineering. We thus propose Twin Agent, a general privilege separation design…

Read at arXiv (research papers)

arXiv (research papers) Akansha Shukla SI

Data Leakage Prevention in Agentic Applications via Preemptive Hardening

Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks. Enforcing required controls consistently is particularly challenging in workflows spanning many codebases and heterogeneous agents. To address this challenge in multi agentic systems, we present a pre-deployment pipeline for scanning, hardening, and validation of agentic…

Read at arXiv (research papers)

arXiv (research papers) Om Narayan SI

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

The Model Context Protocol (MCP) is an open-source standard that allows AI agents to connect to external tools, databases, and services. While this connectivity enables powerful agent capabilities, it also introduces multi-step attacks that existing per-call defenses cannot reliably detect. Attackers can compose individually benign tool invocations into malicious sequences that evade isolated inspection. This paper presents ChainWatch, a sequential detection framework for…

Read at arXiv (research papers)

arXiv (research papers) Jie Li SI

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial…

Read at arXiv (research papers)

arXiv (research papers) Devina Jain SI

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. We present a 21-scenario benchmark for adaptive cross-session attacks against fresh-session LLM defenders: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. A controlled 3 x 3 attacker-defender matrix contains 945 battles. Restricting scoring to the first round yields…

Read at arXiv (research papers)

arXiv (research papers) Xingfu Zhou SI

Salience Induction against Multi-Hop RAG Agents: Threat and Defense

Agentic retrieval-augmented generation (RAG) systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive applications. In Multi-Hop question answering, agents chain facts across documents. Existing defenses focus on content poisoning, which injects false facts, and prompt injection, which embeds directives. We identify a third attack surface: the salience channel, through which fact position, emphasis, framing, and semantic proximity can…

Read at arXiv (research papers)

arXiv (research papers) Soham Gadgil SI

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which malicious instructions can be embedded within persistent files and influence future behavior. In this work, we study prompt injection attacks in memory-based agentic systems using a sandboxed synthetic…

Read at arXiv (research papers)

arXiv (research papers) Sanket Badhe SI

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

Reusable skills are becoming a fundamental building block of Large Language Model (LLM) agents, enabling capabilities to be packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security risks throughout the broader skill lifecycle largely unexplored. In this paper, we present SkillSec-Eval, a lifecycle-aware framework for systematically evaluating the security of…

Read at arXiv (research papers)

arXiv (research papers) Junhui Wang SI

PVDetector: Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents through Policy-Violation Concept Analysis

Large language models (LLMs) are increasingly deployed as purpose-specific agents to handle domain-specific tasks such as customer service and code generation. These agents are expected to comply with not only generic safety guardrails but also purpose-specific restrictions tailored to their designated roles. Such additional restrictions enlarge the attack surface, particularly to prompt injection (PI) attacks. To defend against such attacks, existing detection methods…

Read at arXiv (research papers)

arXiv (research papers) Huihao Jing SI

Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

The capability of LLM agents to function as the ``brain'' of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior and real-world execution outcomes. However, the current literature is fragmented across attack types, applications, and benchmarks. This makes it hard to explain why failures such as prompt injection, tool misuse, and memory…

Read at arXiv (research papers)

arXiv (research papers) SingGuard Team SI

SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification

We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive information extraction, malicious code requests, dangerous tool misuse, and resource exhaustion. We first introduce the NSFA taxonomy, which organizes 185 risk variants into a CIA-triad-grounded hierarchy and is cross-validated against three well-established OWASP guidelines. Based on this taxonomy, we construct a benchmark suite…

Read at arXiv (research papers)

arXiv (research papers) Ruksat Khan Shayoni SI

NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations

Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections. We present NetInjectBench, a 130-scenario benchmark that separates untrusted artifact text, trusted policy metadata, and evaluation labels for network-operation tool use. The sample contains 40 benign, 40 weak-attack, 40 strong-attack, and 10 approved high-impact change scenarios; each is evaluated…

Read at arXiv (research papers)

Journal articles (OpenAlex) Miguel Muñoz, Juan Felipe Espinosa‐Cristia, Raúl Carrasco · Administrative Sciences Geopolitics

Customs Agents Facing State-Driven Technological Changes: Perceptions of the Digitization of Goods Clearance in Chile

Globally, states are incorporating various digital tools with the purpose of accelerating customs management of export and import goods. An example of this is the implementation of electronic single windows that seek to streamline the transmission of information on export and import operations by generating a single data entry point that can be accessed by different interconnected state and private entities. For customs clearance, some States require the collaboration of…

Read at Journal articles (OpenAlex)

arXiv (research papers) Hugo García Cuesta SI

Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models

While Large Language Models (LLMs) have become essential productivity tools, their integration into workflows without adequate safeguards creates significant risks. This paper proposes an open-source, privacy-focused, user-facing firewall designed to secure both web-based and programmatic LLM interactions. The architecture combines a browser extension and a proxy for total traffic interception across both HTTP(S) and WebSocket communications. At its core, a flexible…

Read at arXiv (research papers)

arXiv (research papers) Corban Villa SI

Prismata: Confining Cross-Site Prompt Injection in Web Agents

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning…

Read at arXiv (research papers)

OWASP GenAI Security Project OWASPGenAIProject Editor Security

GenAI and Agentic AI Exploit Roundup Q2 2026

April 1 through June 30 2026 Overview Six selected cases show how AI integrations, coding tools, and browser agents can turn ordinary inputs or delegated access into security exposure. Defenders should constrain tool execution and credentials, preserve input provenance, and monitor the actions agents take. Coverage includes incidents and technical disclosures published during the quarter.

Read at OWASP GenAI Security Project

arXiv (research papers) Aya Spira SI

Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting

The growing adoption of agentic LLM applications has introduced a new threat previously named as promptware. While prior work has established that adversaries can exploit direct channels to LLM applications to apply promptware under weak threat models, many applications do not provide any direct channels that could be exploited for prompt injection beyond the Internet. This raises a question: can attackers exploit LLM applications at scale without any direct channels in…

Read at arXiv (research papers)

Older stories