English
Related papers

Related papers: Spinning Sequence-to-Sequence Models with Meta-Bac…

200 papers

The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security…

Cryptography and Security · Computer Science 2025-05-06 Giorgio Severi , Simona Boboila , John Holodnak , Kendra Kratkiewicz , Rauf Izmailov , Michael J. De Lucia , Alina Oprea

This position paper argues that the AI/ML community should stop overclaiming and retire the label "positive backdoor," and instead treat trigger-activated hidden behaviors as Secret Alignment. Crucially, protective claims based on Secret…

Cryptography and Security · Computer Science 2026-05-28 Jianwei Li , Jung-Eun Kim

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Machine Learning · Computer Science 2025-11-18 Yuting Tan , Yi Huang , Zhuo Li

Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defenses often rely on regularization techniques to reduce…

Cryptography and Security · Computer Science 2024-11-26 Zhen-Ting Liu , Shang-Tse Chen

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Machine Learning · Computer Science 2021-04-26 Jonathan Hayase , Weihao Kong , Raghav Somani , Sewoong Oh

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional…

Machine Learning · Computer Science 2025-07-11 James Chua , Jan Betley , Mia Taylor , Owain Evans

Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…

Cryptography and Security · Computer Science 2025-06-17 Marco Arazzi , Antonino Nocera , Vinod P

Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…

Machine Learning · Computer Science 2021-10-06 Mingjie Sun , Siddhant Agarwal , J. Zico Kolter

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Cryptography and Security · Computer Science 2025-01-07 Shuai Zhao , Meihuizi Jia , Zhongliang Guo , Leilei Gan , Xiaoyu Xu , Xiaobao Wu , Jie Fu , Yichao Feng , Fengjun Pan , Luu Anh Tuan

Textual backdoor attack, as a novel attack model, has been shown to be effective in adding a backdoor to the model during training. Defending against such backdoor attacks has become urgent and important. In this paper, we propose AttDef,…

Computation and Language · Computer Science 2023-08-08 Jiazhao Li , Zhuofeng Wu , Wei Ping , Chaowei Xiao , V. G. Vinod Vydiswaran

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Aniruddha Saha , Ajinkya Tejankar , Soroush Abbasi Koohpayegani , Hamed Pirsiavash

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Machine Learning · Computer Science 2022-07-12 Chang Yue , Peizhuo Lv , Ruigang Liang , Kai Chen

Autonomous vehicles ought to predict the surrounding agents' trajectories to allow safe maneuvers in uncertain and complex traffic situations. As companies increasingly apply trajectory prediction in the real world, security becomes a…

Machine Learning · Computer Science 2024-01-04 Kaouther Messaoud , Kathrin Grosse , Mickael Chen , Matthieu Cord , Patrick Pérez , Alexandre Alahi

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

Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to…

Machine Learning · Computer Science 2023-02-01 Shuaiqi Wang , Jonathan Hayase , Giulia Fanti , Sewoong Oh

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

Computation and Language · Computer Science 2024-10-10 Shuai Zhao , Meihuizi Jia , Luu Anh Tuan , Fengjun Pan , Jinming Wen

As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other. In backdoor…

Machine Learning · Computer Science 2021-10-12 Siddhartha Datta , Giulio Lovisotto , Ivan Martinovic , Nigel Shadbolt

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Cryptography and Security · Computer Science 2025-03-28 Dorde Popovic , Amin Sadeghi , Ting Yu , Sanjay Chawla , Issa Khalil

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu
‹ Prev 1 8 9 10 Next ›