English
Related papers

Related papers: SleeperNets: Universal Backdoor Poisoning Attacks …

200 papers

Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet daily, possibly containing backdoors, and third-party model…

Machine Learning · Computer Science 2025-12-16 Chace Ashcraft , Ted Staley , Josh Carney , Cameron Hickert , Derek Juba , Kiran Karra , Nathan Drenkow

With the rapid development of generative artificial intelligence, particularly large language models a number of sub-fields of deep learning have made significant progress and are now very useful in everyday applications. For…

Machine Learning · Computer Science 2025-04-23 Orson Mengara

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

Computation and Language · Computer Science 2024-05-21 Xuanli He , Qiongkai Xu , Jun Wang , Benjamin I. P. Rubinstein , Trevor Cohn

Reinforcement learning (RL) has been demonstrated suitable to develop agents that play complex games with human-level performance. However, it is not understood how to effectively use RL to perform cybersecurity tasks. To develop such…

Cryptography and Security · Computer Science 2021-03-16 Andres Molina-Markham , Cory Miniter , Becky Powell , Ahmad Ridley

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

Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Multiagent Systems · Computer Science 2022-11-22 Shuo Chen , Yue Qiu , Jie Zhang

In reward-poisoning attacks against reinforcement learning (RL), an attacker can perturb the environment reward $r_t$ into $r_t+\delta_t$ at each step, with the goal of forcing the RL agent to learn a nefarious policy. We categorize such…

Machine Learning · Computer Science 2020-06-24 Xuezhou Zhang , Yuzhe Ma , Adish Singla , Xiaojin Zhu

With the wide application of deep reinforcement learning (DRL) techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable…

Cryptography and Security · Computer Science 2025-10-24 Wu Yichao , Wang Yirui , Ding Panpan , Wang Hailong , Zhu Bingqian , Liu Chun

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

This paper proposes an online environment poisoning algorithm tailored for reinforcement learning agents operating in a black-box setting, where an adversary deliberately manipulates training data to lead the agent toward a mischievous…

Machine Learning · Computer Science 2024-12-03 Jianhui Li , Bokang Zhang , Junfeng Wu

The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized…

Machine Learning · Computer Science 2024-05-27 Mengtong Gao , Yifei Zou , Zuyuan Zhang , Xiuzhen Cheng , Dongxiao Yu

Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to make decisions based on real-world experiences. This approach has significantly advanced AI applications across various domains, notably in smart grid…

Cryptography and Security · Computer Science 2024-02-27 Zheyu Zhang

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Federated learning (FL) has become a popular tool for solving traditional Reinforcement Learning (RL) tasks. The multi-agent structure addresses the major concern of data-hungry in traditional RL, while the federated mechanism protects the…

Machine Learning · Computer Science 2024-01-08 Evelyn Ma , Praneet Rathi , S. Rasoul Etesami

Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abilities on complex logical tasks, such as mathematics and programming. However, we…

Cryptography and Security · Computer Science 2026-04-14 Weiyang Guo , Zesheng Shi , Zeen Zhu , Yuan Zhou , Min Zhang , Jing Li

Backdoor attack has emerged as a major security threat to deep neural networks (DNNs). While existing defense methods have demonstrated promising results on detecting or erasing backdoors, it is still not clear whether robust training…

Machine Learning · Computer Science 2021-12-02 Yige Li , Xixiang Lyu , Nodens Koren , Lingjuan Lyu , Bo Li , Xingjun Ma

Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL backdoor attacks are primarily studied in simulation and often…

Robotics · Computer Science 2026-05-14 Tairan Huang , Qingqing Ye , Yulin Jin , Jiawei Lian , Yaxin Xiao , Yi Wang , Haibo Hu

Backdoors implanted in pre-trained language models (PLMs) can be transferred to various downstream tasks, which exposes a severe security threat. However, most existing backdoor attacks against PLMs are un-targeted and task-specific. Few…

Computation and Language · Computer Science 2024-12-20 Wei Du , Peixuan Li , Boqun Li , Haodong Zhao , Gongshen Liu

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