English
Related papers

Related papers: CAT: Concept-level backdoor ATtacks for Concept Bo…

200 papers

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

The Large Language Models (LLMs) are poised to offer efficient and intelligent services for future mobile communication networks, owing to their exceptional capabilities in language comprehension and generation. However, the extremely high…

Cryptography and Security · Computer Science 2023-09-07 Haomiao Yang , Kunlan Xiang , Mengyu Ge , Hongwei Li , Rongxing Lu , Shui Yu

Concept Bottleneck Models (CBMs) first map raw input(s) to a vector of human-defined concepts, before using this vector to predict a final classification. We might therefore expect CBMs capable of predicting concepts based on distinct…

Artificial Intelligence · Computer Science 2023-02-08 Jack Furby , Daniel Cunnington , Dave Braines , Alun Preece

Voice disorders affect a significant portion of the population, and the ability to diagnose them using automated, non-invasive techniques would represent a substantial advancement in healthcare, improving the quality of life of patients.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-25 Davide Ghia , Gabriele Ciravegna , Alkis Koudounas , Marco Fantini , Erika Crosetti , Giovanni Succo , Tania Cerquitelli

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Cryptography and Security · Computer Science 2025-09-24 Yuan Ma , Jiankang Wei , Yilun Lyu , Kehao Chen , Jingtong Huang

We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional black-box LLMs that rely on limited post-hoc interpretations,…

Computation and Language · Computer Science 2025-09-09 Chung-En Sun , Tuomas Oikarinen , Berk Ustun , Tsui-Wei Weng

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we…

Cryptography and Security · Computer Science 2025-11-17 Shuaitong Liu , Renjue Li , Lijia Yu , Lijun Zhang , Zhiming Liu , Gaojie Jin

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yangming Chen

Backdoor attacks pose a significant threat to neural networks, enabling adversaries to manipulate model outputs on specific inputs, often with devastating consequences, especially in critical applications. While backdoor attacks have been…

Machine Learning · Computer Science 2025-07-30 Zhen Guo , Abhinav Kumar , Reza Tourani

Deep neural networks have achieved remarkable success in computer vision; however, their black-box nature in decision-making limits interpretability and trust, particularly in safety-critical applications. Interpretability is crucial in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ran Eisenberg , Amit Rozner , Ethan Fetaya , Ofir Lindenbaum

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models that would provide…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Andrei Semenov , Vladimir Ivanov , Aleksandr Beznosikov , Alexander Gasnikov

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

Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Schrasing Tong , Antoine Salaun , Vincent Yuan , Annabel Adeyeri , Lalana Kagal

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

The main challenges hindering the adoption of deep learning-based systems in clinical settings are the scarcity of annotated data and the lack of interpretability and trust in these systems. Concept Bottleneck Models (CBMs) offer inherent…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Cristiano Patrício , Luís F. Teixeira , João C. Neves

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

Cryptography and Security · Computer Science 2022-03-30 Arezoo Rajabi , Bhaskar Ramasubramanian , Radha Poovendran

Textual Concept Bottleneck Models (TCBMs) are interpretable-by-design models for text classification that predict a set of salient concepts before making the final prediction. This paper proposes Complete Textual Concept Bottleneck Model…

Computation and Language · Computer Science 2025-05-29 Milan Bhan , Yann Choho , Pierre Moreau , Jean-Noel Vittaut , Nicolas Chesneau , Marie-Jeanne Lesot

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

Cryptography and Security · Computer Science 2021-02-22 Eugene Bagdasaryan , Vitaly Shmatikov

With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…

Cryptography and Security · Computer Science 2025-10-10 Man Hu , Xinyi Wu , Zuofeng Suo , Jinbo Feng , Linghui Meng , Yanhao Jia , Anh Tuan Luu , Shuai Zhao

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Cryptography and Security · Computer Science 2023-10-19 Ganghua Wang , Xun Xian , Jayanth Srinivasa , Ashish Kundu , Xuan Bi , Mingyi Hong , Jie Ding