English
Related papers

Related papers: Low-Loss Subspace Compression for Clean Gains agai…

200 papers

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Cryptography and Security · Computer Science 2025-01-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning while training the LMs…

Computation and Language · Computer Science 2024-06-04 Zongru Wu , Zhuosheng Zhang , Pengzhou Cheng , Gongshen Liu

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

Cryptography and Security · Computer Science 2023-07-20 Alaa Khaddaj , Guillaume Leclerc , Aleksandar Makelov , Kristian Georgiev , Hadi Salman , Andrew Ilyas , Aleksander Madry

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

Cryptography and Security · Computer Science 2026-05-05 Yi Yang , Jinyang Huang , Binbin Liu , Feng-Qi Cui , Xiaokang Zhou , Zhi Liu , Jie Zhang , Meng Li

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

Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…

Machine Learning · Computer Science 2024-11-11 Xiaoyun Xu , Zhuoran Liu , Stefanos Koffas , Shujian Yu , Stjepan Picek

A common observation regarding adversarial attacks is that they mostly give rise to false activation at the penultimate layer to fool the classifier. Assuming that these activation values correspond to certain features of the input, the…

Machine Learning · Computer Science 2021-06-21 Emre Ozfatura , Muhammad Zaid Hameed , Kerem Ozfatura , Deniz Gunduz

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been proposed to mitigate these attacks, the heterogeneous…

Cryptography and Security · Computer Science 2025-11-18 Gorka Abad , Marina Krček , Stefanos Koffas , Behrad Tajalli , Marco Arazzi , Roberto Riaño , Xiaoyun Xu , Zhuoran Liu , Antonino Nocera , Stjepan Picek

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Cryptography and Security · Computer Science 2026-03-05 Bhanu Pallakonda , Mikkel Hindsbo , Sina Ehsani , Prag Mishra

Reinforcement learning (RL) makes an agent learn from trial-and-error experiences gathered during the interaction with the environment. Recently, offline RL has become a popular RL paradigm because it saves the interactions with…

Machine Learning · Computer Science 2024-03-21 Chen Gong , Zhou Yang , Yunpeng Bai , Junda He , Jieke Shi , Kecen Li , Arunesh Sinha , Bowen Xu , Xinwen Hou , David Lo , Tianhao Wang

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many…

Cryptography and Security · Computer Science 2024-12-23 Borja Molina-Coronado

When machine learning training is outsourced to third parties, $backdoor$ $attacks$ become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the…

Cryptography and Security · Computer Science 2022-11-16 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Federated learning (FL) enables multiple clients to collaboratively train machine learning models under the coordination of a central server, while maintaining privacy. However, the server cannot directly monitor the local training…

Machine Learning · Computer Science 2025-07-23 Binbin Ding , Penghui Yang , Sheng-Jun Huang

Since training a large-scale backdoored model from scratch requires a large training dataset, several recent attacks have considered to inject backdoors into a trained clean model without altering model behaviors on the clean data. Previous…

Machine Learning · Computer Science 2022-03-03 Zhiyuan Zhang , Lingjuan Lyu , Weiqiang Wang , Lichao Sun , Xu Sun

Deep neural networks have been shown to be vulnerable to backdoor attacks, which could be easily introduced to the training set prior to model training. Recent work has focused on investigating backdoor attacks on natural images or toy…

Cryptography and Security · Computer Science 2021-01-05 Munachiso Nwadike , Takumi Miyawaki , Esha Sarkar , Michail Maniatakos , Farah Shamout

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

Machine Learning · Computer Science 2017-08-31 Valentina Zantedeschi , Maria-Irina Nicolae , Ambrish Rawat

With the rapid advancement of image generative models, generative data augmentation has become an effective way to enrich training images, especially when only small-scale datasets are available. At the same time, in practical applications,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Ting Xiang , Jinhui Zhao , Changjian Chen , Zhuo Tang

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

Machine Learning · Computer Science 2021-02-12 Pooya Tavallali , Vahid Behzadan , Peyman Tavallali , Mukesh Singhal

The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data. However, FL is susceptible to backdoor attacks where a small…

Cryptography and Security · Computer Science 2022-02-24 Yein Kim , Huili Chen , Farinaz Koushanfar

Backdoor attacks pose a critical threat to machine learning models, causing them to behave normally on clean data but misclassify poisoned data into a poisoned class. Existing defenses often attempt to identify and remove backdoor neurons…

Machine Learning · Computer Science 2025-11-13 Kazuki Iwahana , Yusuke Yamasaki , Akira Ito , Takayuki Miura , Toshiki Shibahara