相关论文: Session Risk Memory (SRM): Temporal Authorization …

Autonomous Vehicles (AVs) must make reliable decisions in dense urban environments where pedestrian behavior is variable, sometimes abnormal, and often unseen during training. Reinforcement learning (RL)-based AV control systems perform…

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model…

Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial prompts. Predominant token-level optimization methods…

We demonstrate how collective memory emerges in decentralized multi-agent systems through the interplay between individual agent memory and environmental trace communication. Our agents maintain internal memory states while depositing…

Vehicles with Automated Driving Systems (ADS) operate in a high-dimensional continuous system with multi-agent interactions. This continuous system features various types of traffic agents (non-homogeneous) governed by continuous-motion…

Construction tasks are inherently unpredictable, with dynamic environments and safety-critical demands posing significant risks to workers. Exoskeletons offer potential assistance but falter without accurate intent recognition across…

In domains such as finance, healthcare, and robotics, managing worst-case scenarios is critical, as failure to do so can lead to catastrophic outcomes. Distributional Reinforcement Learning (DRL) provides a natural framework to incorporate…

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

Longitudinal passive sensing enables continuous health prediction, yet models often fail under cross-dataset distribution shifts. Traditional ML overfits cohort-specific artifacts, while Large Language Models (LLMs) struggle to reason…

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term…

The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are…

Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) models, offering parallel decoding and controllable sampling dynamics while achieving competitive generation quality at scale. Despite…

LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety depend not only on individual model outputs, but also on what…

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…

Reinforcement learning (RL) based post-training for explicit chain-of-thought (e.g., GRPO) improves the reasoning ability of multimodal large-scale reasoning models (MLRMs). But recent evidence shows that it can simultaneously degrade…

Oblivious RAM protocols (ORAMs) allow a client to access data from an untrusted storage device without revealing the access patterns. Typically, the ORAM adversary can observe both read and write accesses. Write-only ORAMs target a more…

Modern adversarial campaigns unfold as sequences of behavioural phases - Reconnaissance, Lateral Movement, Intrusion, and Exfiltration - each often indistinguishable from legitimate traffic when viewed in isolation. Existing intrusion…

Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity, which collectively undermine the robustness of risk…

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…