English
Related papers

Related papers: Lightweight Lipschitz Margin Training for Certifie…

200 papers

Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolutional Networks (ConvNets) on low-dimensional data, such as…

Machine Learning · Computer Science 2023-10-31 Kai Hu , Andy Zou , Zifan Wang , Klas Leino , Matt Fredrikson

Due to their susceptibility to adversarial perturbations, neural networks (NNs) are hardly used in safety-critical applications. One measure of robustness to such perturbations in the input is the Lipschitz constant of the input-output map…

Machine Learning · Computer Science 2021-04-30 Patricia Pauli , Anne Koch , Julian Berberich , Paul Kohler , Frank Allgöwer

Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified…

Machine Learning · Computer Science 2024-12-23 Jiapeng Wu , Atiyeh Ashari Ghomi , David Glukhov , Jesse C. Cresswell , Franziska Boenisch , Nicolas Papernot

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

While multi-step adversarial training is widely popular as an effective defense method against strong adversarial attacks, its computational cost is notoriously expensive, compared to standard training. Several single-step adversarial…

Machine Learning · Computer Science 2021-11-30 Geon Yeong Park , Sang Wan Lee

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiequan Cui , Shu Liu , Liwei Wang , Jiaya Jia

Machine learning models have demonstrated remarkable success across diverse domains but remain vulnerable to adversarial attacks. Empirical defense mechanisms often fail, as new attacks constantly emerge, rendering existing defenses…

Machine Learning · Computer Science 2024-10-25 Anupriya Kumari , Devansh Bhardwaj , Sukrit Jindal

To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds for a small but…

Machine Learning · Computer Science 2023-03-10 Mark Niklas Müller , Franziska Eckert , Marc Fischer , Martin Vechev

Certified defenses against small-norm adversarial examples have received growing attention in recent years; though certified accuracies of state-of-the-art methods remain far below their non-robust counterparts, despite the fact that…

Machine Learning · Computer Science 2023-01-24 Klas Leino

Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the…

Machine Learning · Computer Science 2022-03-04 Mo Zhou , Vishal M. Patel

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen…

Machine Learning · Computer Science 2023-05-18 Thomas Altstidl , David Dobre , Björn Eskofier , Gauthier Gidel , Leo Schwinn

In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional L_p "norms"…

Machine Learning · Computer Science 2022-03-18 Alexander Levine , Soheil Feizi

Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations, enabling powerful downstream capabilities like few-shot…

Machine Learning · Computer Science 2025-10-13 Yuni Lai , Xiaoyu Xue , Linghui Shen , Yulun Wu , Gaolei Li , Song Guo , Kai Zhou , Bin Xiao

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Machine Learning · Computer Science 2026-04-28 Liaoyaqi Wang , Chunsheng Zuo , William Jurayj , Benjamin Van Durme , Anqi Liu

Multi-modal models have shown a promising capability to effectively integrate information from various sources, yet meanwhile, they are found vulnerable to pervasive perturbations, such as uni-modal attacks and missing conditions. To…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Zequn Yang , Yake Wei , Ce Liang , Di Hu

Neural networks are often highly sensitive to input and weight perturbations. This sensitivity has been linked to pathologies such as vulnerability to adversarial examples, divergent training, and overfitting. To combat these problems, past…

Machine Learning · Computer Science 2025-07-18 Laker Newhouse , R. Preston Hess , Franz Cesista , Andrii Zahorodnii , Jeremy Bernstein , Phillip Isola

Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted adversarial examples with higher transferability than non-targeted…

Computer Vision and Pattern Recognition · Computer Science 2023-03-08 Juanjuan Weng , Zhiming Luo , Zhun Zhong , Shaozi Li , Nicu Sebe

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…

Machine Learning · Computer Science 2019-10-21 Florian Tramèr , Dan Boneh

Recently, Zhang et al. (2021) developed a new neural network architecture based on $\ell_\infty$-distance functions, which naturally possesses certified $\ell_\infty$ robustness by its construction. Despite the novel design and theoretical…

Machine Learning · Computer Science 2022-03-16 Bohang Zhang , Du Jiang , Di He , Liwei Wang

Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples during training often…

Machine Learning · Computer Science 2019-10-28 Ali Shafahi , Amin Ghiasi , Furong Huang , Tom Goldstein