English
Related papers

Related papers: GREAT: Generalizable Backdoor Attacks in RLHF via …

200 papers

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in…

Cryptography and Security · Computer Science 2021-03-05 Anh Nguyen , Anh Tran

Backdoor attacks have been demonstrated as a security threat for machine learning models. Traditional backdoor attacks intend to inject backdoor functionality into the model such that the backdoored model will perform abnormally on inputs…

Machine Learning · Computer Science 2023-04-19 Jing Xu , Gorka Abad , Stjepan Picek

The rapid integration of Generative AI (GenAI) into various applications necessitates robust risk management strategies which includes Red Teaming (RT) - an evaluation method for simulating adversarial attacks. Unfortunately, RT for GenAI…

Cryptography and Security · Computer Science 2025-05-01 Tam n. Nguyen

\textbf{G}raph \textbf{N}eural \textbf{N}etworks~(GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their…

Cryptography and Security · Computer Science 2024-12-24 Jiangtong Li , Dungy Liu , Dawei Cheng , Changchun Jiang

Backdoor attacks have become a critical threat to deep neural networks (DNNs), drawing many research interests. However, most of the studied attacks employ a single type of trigger. Consequently, proposed backdoor defenders often rely on…

Cryptography and Security · Computer Science 2025-01-14 Duc Anh Vu , Anh Tuan Tran , Cong Tran , Cuong Pham

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

Computation and Language · Computer Science 2026-04-21 San Kim , Gary Geunbae Lee

Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized…

Machine Learning · Computer Science 2025-10-29 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

Reliable automatic hate speech (HS) detection systems must adapt to the in-flow of diverse new data to curtail hate speech. However, hate speech detection systems commonly lack generalizability in identifying hate speech dissimilar to data…

Computation and Language · Computer Science 2023-12-19 Shi Yin Hong , Susan Gauch

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Text-to-image diffusion models can generate realistic images based on textual inputs, enabling users to convey their opinions visually through language. Meanwhile, within language, emotion plays a crucial role in expressing personal…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Tianyu Wei , Shanmin Pang , Qi Guo , Yizhuo Ma , Xiaofeng Cao , Qing Guo

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these…

Cryptography and Security · Computer Science 2024-12-25 Sara Price , Arjun Panickssery , Sam Bowman , Asa Cooper Stickland

Heterogeneous graph neural networks (HGNNs) have achieved strong performance in many real-world applications, yet targeted backdoor poisoning on heterogeneous graphs remains less studied. We consider backdoor attacks for heterogeneous node…

Machine Learning · Computer Science 2026-01-01 Honglin Gao , Lan Zhao , Junhao Ren , Xiang Li , Gaoxi Xiao

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is…

Machine Learning · Computer Science 2025-09-10 Yanxin Yang , Ming Hu , Xiaofei Xie , Yue Cao , Pengyu Zhang , Yihao Huang , Mingsong Chen

Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vulnerable to backdoor attacks, which inject a shared backdoor…

Cryptography and Security · Computer Science 2024-07-15 Yuxin Yang , Qiang Li , Jinyuan Jia , Yuan Hong , Binghui Wang

Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences.…

Machine Learning · Computer Science 2023-12-04 Hanze Dong , Wei Xiong , Deepanshu Goyal , Yihan Zhang , Winnie Chow , Rui Pan , Shizhe Diao , Jipeng Zhang , Kashun Shum , Tong Zhang

Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g.,…

Machine Learning · Computer Science 2026-04-20 Songtao Wang , Quang Hieu Pham , Fangcong Yin , Xinpeng Wang , Jocelyn Qiaochu Chen , Greg Durrett , Xi Ye

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Cryptography and Security · Computer Science 2025-06-09 Yuan Xun , Siyuan Liang , Xiaojun Jia , Xinwei Liu , Xiaochun Cao

The foundation models (FMs) have been used to generate synthetic public datasets for the heterogeneous federated learning (HFL) problem where each client uses a unique model architecture. However, the vulnerabilities of integrating FMs,…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-01 Xi Li , Chen Wu , Jiaqi Wang