Related papers: Trojan Playground: A Reinforcement Learning Framew…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Pre-trained vision models (PVMs) have become a dominant component due to their exceptional performance when fine-tuned for downstream tasks. However, the presence of backdoors within PVMs poses significant threats. Unfortunately, existing…

Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks. Understanding attack tactics helps improve the robustness of RSs. We intend to develop efficient attack methods that use limited…

This innovative practice category paper presents an innovative framework for teaching Reinforcement Learning (RL) at the undergraduate level. Recognizing the challenges posed by the complex theoretical foundations of the subject and the…

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…

Reinforcement Learning (RL) has shown remarkable success in solving relatively complex tasks, yet the deployment of RL systems in real-world scenarios poses significant challenges related to safety and robustness. This paper aims to…

Increased dependence on networked, software based control has escalated the vulnerabilities of Cyber Physical Systems (CPSs). Detection and monitoring components developed leveraging dynamical systems theory are often employed as…

Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory tracking and pose stabilization. However, their reliance on potentially untrusted training pipelines or supply chains introduces…

When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints. In many real-world problems, however, the constraints are often hard to specify…

Due to the ever-growing demands for electronic chips in different sectors the semiconductor companies have been mandated to offshore their manufacturing processes. This unwanted matter has made security and trustworthiness of their…

Due to cost benefits, supply chains of integrated circuits (ICs) are largely outsourced nowadays. However, passing ICs through various third-party providers gives rise to many security threats, like piracy of IC intellectual property or…

A massive threat to the modern and complex IC production chain is the use of untrusted off-shore foundries which are able to infringe valuable hardware design IP or to inject hardware Trojans causing severe loss of safety and security.…

Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan…

Deep Neural Networks (DNNs) have found extensive applications in safety-critical artificial intelligence systems, such as autonomous driving and facial recognition systems. However, recent research has revealed their susceptibility to…

Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing. Despite these advances, a…

Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However,…

The growing use of third-party hardware accelerators (e.g., FPGAs, ASICs) for deep neural networks (DNNs) introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify…

In Natural Language Processing (NLP), intelligent neuron models can be susceptible to textual Trojan attacks. Such attacks occur when Trojan models behave normally for standard inputs but generate malicious output for inputs that contain a…

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution thanks to their capability of autonomously…

Automating penetration testing is crucial for enhancing cybersecurity, yet current Large Language Models (LLMs) face significant limitations in this domain, including poor error handling, inefficient reasoning, and an inability to perform…