Related papers: Regular Expression Denial of Service Induced by Ba…

Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithms often assume instantaneous perception of the environment. We study random sensor delays in POMDPs, where observations may arrive…

Large language models (LLMs) have demonstrated impressive performance and have come to dominate the field of natural language processing (NLP) across various tasks. However, due to their strong instruction-following capabilities and…

Recent work has proposed the concept of backdoor attacks on deep neural networks (DNNs), where misbehaviors are hidden inside "normal" models, only to be triggered by very specific inputs. In practice, however, these attacks are difficult…

Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks. The objectives of these attacks are twofold: induce pre-determined, adversarial behavior in…

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms to detect and diagnose these failures. We present an…

Bank crisis is challenging to define but can be manifested through bank contagion. This study presents a comprehensive framework grounded in nonlinear time series analysis to identify potential early warning signals (EWS) for impending…

Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm,…

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.…

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…

Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning…

We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can be equally exploited. We leverage 20 different types of…

Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that induce desired misclassifications in the models. Such risks impede the application of machine learning in security-sensitive domains.…

Modern language models fail a fundamental requirement of trustworthy intelligence: knowing when not to answer. Despite achieving impressive accuracy on benchmarks, these models produce confident hallucinations, even when wrong answers carry…

When tasks change over time, meta-transfer learning seeks to improve the efficiency of learning a new task via both meta-learning and transfer-learning. While the standard attention has been effective in a variety of settings, we question…

Automated penetration testing (AutoPT) based on reinforcement learning (RL) has proven its ability to improve the efficiency of vulnerability identification in information systems. However, RL-based PT encounters several challenges,…

Penetration Testing plays a critical role in evaluating the security of a target network by emulating real active adversaries. Deep Reinforcement Learning (RL) is seen as a promising solution to automating the process of penetration tests…

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against backdoor attacks…