Related papers: Enforcing Benign Trajectories: A Behavioral Firewa…

Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strategic adaptation at scale, challenging security architectures…

The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal…

LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of attacks, such as tool poisoning and malicious instructions, that compromise their execution…

Active Directory (AD) is the default security management system for Windows domain networks. An AD environment naturally describes an attack graph where nodes represent computers/accounts/security groups, and edges represent existing…

Autonomous agents such as Claude Code and Codex now operate for hours or even days. Understanding their runtime behavior has become critical for downstream tasks such as diagnosing inefficiencies, fixing bugs, and ensuring better oversight.…

We propose a foundational runtime actuarial layer for autonomous AI agents in which every side-effect-bearing action carries a time-consistent, counterfactual risk toll computed against a contractually fixed safe default, inside an explicit…

Coding agents represent a new paradigm in automated software engineering, combining the reasoning capabilities of Large Language Models (LLMs) with tool-augmented interaction loops. However, coding agents still have severe limitations.…

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

With the wide application of multimodal foundation models in intelligent agent systems, scenarios such as mobile device control, intelligent assistant interaction, and multimodal task execution are gradually relying on such large…

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers…

Coworking AI agents operating within local file systems are rapidly emerging as a paradigm in human-AI interaction; however, effective personalization remains limited by severe data constraints, as strict privacy barriers and the difficulty…

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs…

Advanced Persistent Threats (APTs) are sophisticated, long-term cyberattacks that are difficult to detect because they operate stealthily and often blend into normal system behavior. This paper presents a neuro-symbolic anomaly detection…

Web traffic has evolved to include both human users and automated agents, ranging from benign web crawlers to adversarial scanners such as those capable of credential stuffing, command injection, and account hijacking at the web scale. The…