English
Related papers

Related papers: Cost-Minimized Label-Flipping Poisoning Attack to …

200 papers

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to…

Cryptography and Security · Computer Science 2025-06-03 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Computation and Language · Computer Science 2022-04-28 Leilei Gan , Jiwei Li , Tianwei Zhang , Xiaoya Li , Yuxian Meng , Fei Wu , Yi Yang , Shangwei Guo , Chun Fan

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

Computation and Language · Computer Science 2024-10-28 Xin Mao , Feng-Lin Li , Huimin Xu , Wei Zhang , Wang Chen , Anh Tuan Luu

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Cryptography and Security · Computer Science 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying…

Cryptography and Security · Computer Science 2025-06-30 Stanley Wu , Ronik Bhaskar , Anna Yoo Jeong Ha , Shawn Shan , Haitao Zheng , Ben Y. Zhao

The distributed nature of local differential privacy (LDP) invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular…

Cryptography and Security · Computer Science 2025-06-18 Xiaolin Li , Ninghui Li , Boyang Wang , Wenhai Sun

Rollups have become the de facto scalability solution for Ethereum, securing more than $55B in assets. They achieve scale by executing transactions on a Layer 2 ledger, while periodically posting data and finalizing state on the Layer 1,…

Cryptography and Security · Computer Science 2025-09-23 Stefanos Chaliasos , Conner Swann , Sina Pilehchiha , Nicolas Mohnblatt , Benjamin Livshits , Assimakis Kattis

Recent advancements in large language models (LLMs) have led to their increased application across various tasks, with reinforcement learning from human feedback (RLHF) being a crucial part of their training to align responses with user…

Computation and Language · Computer Science 2024-10-29 Ben Hauptvogel , Malte Ostendorff , Georg Rehm , Sebastian Möller

Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is derived as a bandit problem in which the whole response is…

Computation and Language · Computer Science 2025-04-16 Aiwei Liu , Haoping Bai , Zhiyun Lu , Yanchao Sun , Xiang Kong , Simon Wang , Jiulong Shan , Albin Madappally Jose , Xiaojiang Liu , Lijie Wen , Philip S. Yu , Meng Cao

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

We consider the problem of false data injection attacks modeled as additive disturbances in various parts of a general LTI feedback system and derive necessary and sufficient conditions for the existence of stealthy unbounded attacks. We…

Systems and Control · Computer Science 2017-07-19 Nabil H. Hirzallah , Petros G. Voulgaris

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

Machine Learning · Computer Science 2023-11-21 Huayu Li , Gregory Ditzler

We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting…

Machine Learning · Computer Science 2026-05-21 Richa Verma , Bavish Kulur , Sanjay Chawla , Balaraman Ravindran

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

Machine Learning · Computer Science 2021-10-13 Bingyin Zhao , Yingjie Lao

Programmatic weak supervision (PWS) significantly reduces human effort for labeling data by combining the outputs of user-provided labeling functions (LFs) on unlabeled datapoints. However, the quality of the generated labels depends…

Machine Learning · Computer Science 2025-06-05 Chenjie Li , Amir Gilad , Boris Glavic , Zhengjie Miao , Sudeepa Roy

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption,…

Machine Learning · Computer Science 2026-03-24 Yuhao Du , Zhuo Li , Pengyu Cheng , Zhihong Chen , Yuejiao Xie , Xiang Wan , Anningzhe Gao

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Computation and Language · Computer Science 2024-12-10 Junru Lu , Jiazheng Li , Siyu An , Meng Zhao , Yulan He , Di Yin , Xing Sun

There has been recent interest in leveraging federated learning (FL) for radio signal classification tasks. In FL, model parameters are periodically communicated from participating devices, training on their own local datasets, to a central…

Signal Processing · Electrical Eng. & Systems 2023-01-24 Su Wang , Rajeev Sahay , Christopher G. Brinton

Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: that committed tokens are permanent. We show that violating this assumption, by re-masking committed refusal tokens and injecting a short…

Computation and Language · Computer Science 2026-04-14 Arth Singh