Related papers: Towards Optimal Agentic Architectures for Offensiv…
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.…
LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…
Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external…
Agentic AI systems, which build on Large Language Models (LLMs) and interact with tools and memory, have rapidly advanced in capability and scope. Yet, since LLMs have been shown to struggle in multilingual settings, typically resulting in…
Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…
We present AgentOptics, an agentic AI framework for high-fidelity, autonomous optical system control built on the Model Context Protocol (MCP). AgentOptics interprets natural language tasks and executes protocol-compliant actions on…
Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…
Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…
Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is…
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…
Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…
LLM-based multi-agent systems are increasingly deployed for payment workflows, yet prevailing metrics, Task Success Rate (TSR) and Agent Handoff F1-Score (HF1), capture only final outcomes or unordered routing decisions. We introduce the…
LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve…
The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service (DoS) risks, Automatic Exploit Generation (AEG) systems suffer from semantic blindness, and Large…
Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…
Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…