English
Related papers

Related papers: PolicyCleanse: Backdoor Detection and Mitigation i…

200 papers

Reinforcement learning (RL) has advanced greatly in the past few years with the employment of effective deep neural networks (DNNs) on the policy networks. With the great effectiveness came serious vulnerability issues with DNNs that small…

Machine Learning · Computer Science 2018-07-06 Edgar Tretschk , Seong Joon Oh , Mario Fritz

Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making applications, including robotics, healthcare, smart grids, and finance. Recent studies reveal that adversaries can implant…

Cryptography and Security · Computer Science 2025-11-19 Mingxuan Zhang , Oubo Ma , Kang Wei , Songze Li , Shouling Ji

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Cryptography and Security · Computer Science 2025-12-05 Bingyin Zhao , Yingjie Lao

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

Cryptography and Security · Computer Science 2017-12-18 Xinyun Chen , Chang Liu , Bo Li , Kimberly Lu , Dawn Song

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…

Cryptography and Security · Computer Science 2019-06-24 Liang Tong , Aron Laszka , Chao Yan , Ning Zhang , Yevgeniy Vorobeychik

In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting…

Artificial Intelligence · Computer Science 2021-12-20 Jasmina Gajcin , Rahul Nair , Tejaswini Pedapati , Radu Marinescu , Elizabeth Daly , Ivana Dusparic

We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that will remain dormant…

Cryptography and Security · Computer Science 2022-11-04 Feisi Fu , Panagiota Kiourti , Wenchao Li

Most existing policy learning solutions require the learning agents to receive high-quality supervision signals such as well-designed rewards in reinforcement learning (RL) or high-quality expert demonstrations in behavioral cloning (BC).…

Machine Learning · Computer Science 2021-11-03 Jingkang Wang , Hongyi Guo , Zhaowei Zhu , Yang Liu

Manipulating the interaction trajectories between the intelligent agent and the environment can control the agent's training and behavior, exposing the potential vulnerabilities of reinforcement learning (RL). For example, in Cyber-Physical…

Machine Learning · Computer Science 2024-11-21 Zhi Luo , Xiyuan Yang , Pan Zhou , Di Wang

Downstream fine-tuning of vision-language-action (VLA) models enhances robotics, yet exposes the pipeline to backdoor risks. Attackers can pretrain VLAs on poisoned data to implant backdoors that remain stealthy but can trigger harmful…

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

Machine Learning · Computer Science 2024-02-06 Xinglong Zhang , Yaoqian Peng , Biao Luo , Wei Pan , Xin Xu , Haibin Xie

Federated Learning (FL) enables collaborative deep learning training across multiple participants without exposing sensitive personal data. However, the distributed nature of FL and the unvetted participants' data makes it vulnerable to…

Machine Learning · Computer Science 2023-04-24 Manaar Alam , Hithem Lamri , Michail Maniatakos

Hidden confounders that influence both states and actions can bias policy learning in reinforcement learning (RL), leading to suboptimal or non-generalizable behavior. Most RL algorithms ignore this issue, learning policies from…

Machine Learning · Computer Science 2025-06-09 Thanh Vinh Vo , Young Lee , Haozhe Ma , Chien Lu , Tze-Yun Leong

Trading markets represent a real-world financial application to deploy reinforcement learning agents, however, they carry hard fundamental challenges such as high variance and costly exploration. Moreover, markets are inherently a…

Machine Learning · Computer Science 2021-07-20 Yue Gao , Kry Yik Chau Lui , Pablo Hernandez-Leal

Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. To ensure safety during and after training process, existing methods tend to adopt overly conservative policy to avoid unsafe…

Machine Learning · Computer Science 2023-06-27 Xiao Zhang , Hai Zhang , Hongtu Zhou , Chang Huang , Di Zhang , Chen Ye , Junqiao Zhao

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

In the field of autonomous robots, reinforcement learning (RL) is an increasingly used method to solve the task of dynamic obstacle avoidance for mobile robots, autonomous ships, and drones. A common practice to train those agents is to use…

Robotics · Computer Science 2022-12-09 Fabian Hart , Ostap Okhrin

Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This…

Computer Vision and Pattern Recognition · Computer Science 2017-10-04 Yen-Chen Lin , Ming-Yu Liu , Min Sun , Jia-Bin Huang

Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a safety guide based on model predictive control (MPC) with a…

Machine Learning · Computer Science 2022-03-30 Samuel Pfrommer , Tanmay Gautam , Alec Zhou , Somayeh Sojoudi

We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment. We demonstrate the intrinsic vulnerability of…

Machine Learning · Computer Science 2023-07-18 Yinglun Xu , Qi Zeng , Gagandeep Singh