English
Related papers

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

200 papers

With the advent of deep learning methods, Neural Machine Translation (NMT) systems have become increasingly powerful. However, deep learning based systems are susceptible to adversarial attacks, where imperceptible changes to the input can…

Computation and Language · Computer Science 2023-06-27 Vyas Raina , Mark Gales

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

Computation and Language · Computer Science 2026-05-28 Snehasis Mukhopadhyay

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

Cryptography and Security · Computer Science 2024-10-01 Qin Liu , Wenjie Mo , Terry Tong , Jiashu Xu , Fei Wang , Chaowei Xiao , Muhao Chen

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Cryptography and Security · Computer Science 2024-12-03 Pengfei He , Yue Xing , Han Xu , Jie Ren , Yingqian Cui , Shenglai Zeng , Jiliang Tang , Makoto Yamada , Mohammad Sabokrou

Recent researches have shown that Large Language Models (LLMs) are susceptible to a security threat known as Backdoor Attack. The backdoored model will behave well in normal cases but exhibit malicious behaviours on inputs inserted with a…

Cryptography and Security · Computer Science 2024-04-04 Yunzhuo Hao , Wenkai Yang , Yankai Lin

The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their…

Computation and Language · Computer Science 2024-07-09 Weimin Lyu , Zexin Bi , Fusheng Wang , Chao Chen

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Computation and Language · Computer Science 2023-09-14 Pavel Burnyshev , Elizaveta Kostenok , Alexey Zaytsev

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…

Cryptography and Security · Computer Science 2023-12-14 Peixin Zhang , Jun Sun , Mingtian Tan , Xinyu Wang

Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the…

Machine Learning · Computer Science 2024-01-09 Yujing Jiang , Xingjun Ma , Sarah Monazam Erfani , Yige Li , James Bailey

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Artificial Intelligence · Computer Science 2026-02-03 Abhishek Mishra , Mugilan Arulvanan , Reshma Ashok , Polina Petrova , Deepesh Suranjandass , Donnie Winkelmann

Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or…

Cryptography and Security · Computer Science 2026-04-06 Oğuzhan Ersoy , Nikolay Blagoev , Jona te Lintelo , Stefanos Koffas , Marina Krček , Stjepan Picek

We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "meta-instructions" that control how models answer users'…

Cryptography and Security · Computer Science 2025-06-16 Tingwei Zhang , Collin Zhang , John X. Morris , Eugene Bagdasarian , Vitaly Shmatikov

The frustratingly fragile nature of neural network models make current natural language generation (NLG) systems prone to backdoor attacks and generate malicious sequences that could be sexist or offensive. Unfortunately, little effort has…

Computation and Language · Computer Science 2023-10-10 Xiaofei Sun , Xiaoya Li , Yuxian Meng , Xiang Ao , Lingjuan Lyu , Jiwei Li , Tianwei Zhang

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

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…

Cryptography and Security · Computer Science 2021-04-06 Yiming Li , Yanjie Li , Yalei Lv , Yong Jiang , Shu-Tao Xia

Machine Learning (ML) has automated a multitude of our day-to-day decision making domains such as education, employment and driving automation. The continued success of ML largely depends on our ability to trust the model we are using.…

Machine Learning · Computer Science 2022-04-01 Sakshi Udeshi , Shanshan Peng , Gerald Woo , Lionell Loh , Louth Rawshan , Sudipta Chattopadhyay

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

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

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Cryptography and Security · Computer Science 2024-10-16 Shaokui Wei , Hongyuan Zha , Baoyuan Wu