相关论文: Multi-Axis Trust Modeling for Interpretable Accoun…

Hallucination remains a major reliability barrier for production LLM systems, particularly in multi-agent pipelines where unsupported claims can propagate unchecked across stages. This paper adapts a HOPE-inspired Nested Learning…

Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…

As Large Language Models (LLMs) integrate into critical global infrastructure, the assumption that safety alignment transfers zero-shot from English to other languages remains a dangerous blind spot. This study presents a systematic audit…

Driver assistance systems support drivers in operating vehicles in a safe, comfortable and efficient way, and thus may induce changes in traffic flow characteristics. This paper puts forward a receding horizon control framework to model…

Recently, a growing body of research has focused on either optimizing CTR model architectures to better model feature interactions or refining training objectives to aid parameter learning, thereby achieving better predictive performance.…

There is a dynamic escalation and extension in the new infrastructure, educating personnel and licensing new computer programs in the field of IT, due to the emergence of Cloud Computing (CC) paradigm. It has become a quick growing segment…

The deployment of multimodal models in high-stakes domains, such as self-driving vehicles and medical diagnostics, demands not only strong predictive performance but also reliable mechanisms for detecting failures. In this work, we address…

Leaking information about the execution behavior of critical real-time tasks may lead to serious consequences, including violations of temporal constraints and even severe failures. We study information leakage for a special class of…

Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g.…

This paper proposes an anomaly detection method based on federated learning to address key challenges in multi-tenant cloud environments, including data privacy leakage, heterogeneous resource behavior, and the limitations of centralized…

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling,…

Truly intelligent systems are expected to make critical decisions with incomplete and uncertain data. Active feature acquisition (AFA), where features are sequentially acquired to improve the prediction, is a step towards this goal.…

Embodied AI agents exploit reward signal flaws through reward hacking, achieving high proxy scores while failing true objectives. We introduce Mechanistically Interpretable Task Decomposition (MITD), a hierarchical transformer architecture…

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass…

TRUST Agents is a collaborative multi-agent framework for explainable fact verification and fake news detection. Rather than treating verification as a simple true-or-false classification task, the system identifies verifiable claims,…

Research on Knowledge Tracing (KT) models traditionally focuses on improving predictive accuracy. However, responsible real-world deployment requires models to know when to defer uncertain predictions to a human teacher. We introduce an…

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

AI-powered edge computing security is moving Intelligent Transportation Systems (ITS) from passive, rule-based protections to proactive, smart, zero-touch, self-sufficient safeguards that neutralize threats in milliseconds. As…

Academic integrity continues to face the persistent challenge of examination cheating. Traditional invigilation relies on human observation, which is inefficient, costly, and prone to errors at scale. Although some existing AI-powered…