Related papers: HunterAgent: Neuro-Symbolic Attack Trace Reconstru…

Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent limitations in trustworthiness, including hallucinations, instability, and a lack of transparency.…

Conventional Retrieval Augmented Generation (RAG) approaches are common in text-based applications. However, they struggle with structured, interconnected datasets like knowledge graphs, where understanding underlying relationships is…

Large Language Models (LLMs) have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of…

Dialogue systems powered by large pre-trained language models (LM) exhibit an innate ability to deliver fluent and natural-looking responses. Despite their impressive generation performance, these models can often generate factually…

We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-bearing perturbations (e.g., paraphrase, synonym) alter final answers more often than…

Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming analysts with logs requiring rapidly evolving expertise. Conventional machine-learning detectors…

Hallucinations, the generation of apparently convincing yet false statements, remain a major barrier to the safe deployment of LLMs. Building on the strong performance of self-detection methods, we examine the use of structured knowledge…

LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…

Fault diagnosis of lithium-ion batteries is critical for system safety. While existing deep learning methods exhibit superior detection accuracy, their "black-box" nature hinders interpretability. Furthermore, restricted by binary…

Advanced Persistent Threat (APT) is challenging to detect due to prolonged duration, infrequent occurrence, and adept concealment techniques. Existing approaches primarily concentrate on the observable traits of attack behaviors, neglecting…

Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Outcome-Aware Tool Selection (OATS), which interpolates tool…

Recent advancements in Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) have demonstrated tremendous potential in diverse task scenarios. Nonetheless, existing agentic systems typically rely on predefined agent-role design…

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based…

The adoption of Large Language Models (LLMs) in scientific writing promises efficiency but risks introducing informational entropy. While "hallucinated papers" are a known artifact, the systematic degradation of valid citation chains…

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an…

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…

Large language models (LLMs) have recently shown strong potential in modeling relational structures. However, existing approaches remain fundamentally graph-centric: they focus on processing pairwise graph structures into tokens that LLMs…

This project explores large language models (LLMs) for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems suffer from high false positive rates, semantic blindness, and data scarcity, as logs are…

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…