English
Related papers

Related papers: PolicyCleanse: Backdoor Detection and Mitigation i…

200 papers

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…

Machine Learning · Computer Science 2025-06-04 Ethan Rathbun , Alina Oprea , Christopher Amato

Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…

Systems and Control · Electrical Eng. & Systems 2021-11-24 Juan Cervino , Juan Andres Bazerque , Miguel Calvo-Fullana , Alejandro Ribeiro

Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…

Cryptography and Security · Computer Science 2025-06-12 Li Changjiang , Liang Jiacheng , Cao Bochuan , Chen Jinghui , Wang Ting

Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the…

Cryptography and Security · Computer Science 2023-03-01 Chong Fu , Xuhong Zhang , Shouling Ji , Ting Wang , Peng Lin , Yanghe Feng , Jianwei Yin

The growing prospect of deep reinforcement learning (DRL) being used in cyber-physical systems has raised concerns around safety and robustness of autonomous agents. Recent work on generating adversarial attacks have shown that it is…

Machine Learning · Computer Science 2018-07-18 Aaron J. Havens , Zhanhong Jiang , Soumik Sarkar

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Felix Hsieh , Huy H. Nguyen , AprilPyone MaungMaung , Dmitrii Usynin , Isao Echizen

This paper utilizes Reinforcement Learning (RL) as a means to automate the Hardware Trojan (HT) insertion process to eliminate the inherent human biases that limit the development of robust HT detection methods. An RL agent explores the…

Machine Learning · Computer Science 2022-04-12 Amin Sarihi , Ahmad Patooghy , Peter Jamieson , Abdel-Hameed A. Badawy

Current Hardware Trojan (HT) detection techniques are mostly developed based on a limited set of HT benchmarks. Existing HT benchmark circuits are generated with multiple shortcomings, i.e., i) they are heavily biased by the designers'…

Cryptography and Security · Computer Science 2024-03-22 Amin Sarihi , Ahmad Patooghy , Peter Jamieson , Abdel-Hameed A. Badawy

With the surge of Machine Learning (ML), An emerging amount of intelligent applications have been developed. Deep Neural Networks (DNNs) have demonstrated unprecedented performance across various fields such as medical diagnosis and…

Cryptography and Security · Computer Science 2022-04-12 Xinqiao Zhang , Huili Chen , Ke Huang , Farinaz Koushanfar

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Cryptography and Security · Computer Science 2025-01-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated. We show how to exploit the typically smooth dynamics…

Artificial Intelligence · Computer Science 2018-01-29 Gal Dalal , Krishnamurthy Dvijotham , Matej Vecerik , Todd Hester , Cosmin Paduraru , Yuval Tassa

Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once…

Machine Learning · Computer Science 2021-03-18 Yingqi Liu , Guangyu Shen , Guanhong Tao , Zhenting Wang , Shiqing Ma , Xiangyu Zhang

Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targeted labels in the…

Cryptography and Security · Computer Science 2019-03-19 Zhaoyuan Yang , Naresh Iyer , Johan Reimann , Nurali Virani

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

Machine Learning · Computer Science 2022-03-07 Annie Xie , Shagun Sodhani , Chelsea Finn , Joelle Pineau , Amy Zhang

Backdoor attacks pose a serious threat to deep reinforcement learning (DRL). Current defenses typically rely on reward anomalies to reverse-engineer triggers and model finetuning to remove backdoors. However, complex trigger patterns…

Artificial Intelligence · Computer Science 2026-05-08 Yinbo Yu , Xueyu Yin , Jiadai Wang , Chunwei Tian , Sai Xu , Qi Zhu , Daoqiang Zhang

Reinforcement learning (RL) agents show great promise in solving sequential decision-making tasks. However, validating the reliability and performance of the agent policies' behavior for deployment remains challenging. Most reinforcement…

Software Engineering · Computer Science 2025-09-01 Jørn Eirik Betten , Quentin Mazouni , Dennis Gross , Pedro Lind , Helge Spieker

Deep Learning (DL) has become a key technology that assists radio frequency (RF) signal classification applications, such as modulation classification. However, the DL models are vulnerable to adversarial machine learning threats, such as…

Cryptography and Security · Computer Science 2026-03-27 Younes Salmi , Hanna Bogucka

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

Backdoors pose a serious threat to machine learning, as they can compromise the integrity of security-critical systems, such as self-driving cars. While different defenses have been proposed to address this threat, they all rely on the…

Cryptography and Security · Computer Science 2025-02-04 Alexander Warnecke , Julian Speith , Jan-Niklas Möller , Konrad Rieck , Christof Paar

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…