English
Related papers

Related papers: Improving Alignment and Robustness with Circuit Br…

200 papers

Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy…

Machine Learning · Computer Science 2023-10-03 Yanjie Li , Bin Xie , Songtao Guo , Yuanyuan Yang , Bin Xiao

Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of…

Machine Learning · Statistics 2018-02-09 Thilo Strauss , Markus Hanselmann , Andrej Junginger , Holger Ulmer

AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…

Machine Learning · Computer Science 2024-10-10 Walt Woods , Alexander Grushin , Simon Khan , Alvaro Velasquez

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

Machine Learning · Computer Science 2026-05-14 Lilin Zhang , Yimo Guo , Yue Li , Jiancheng Shi , Xianggen Liu

Circuits are supposed to accurately describe how a neural network performs a specific task, but do they really? We evaluate three circuits found in the literature (IOI, greater-than, and docstring) in an adversarial manner, considering…

Machine Learning · Computer Science 2024-07-23 Niels uit de Bos , Adrià Garriga-Alonso

Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Gabriel Resende Machado , Eugênio Silva , Ronaldo Ribeiro Goldschmidt

Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a…

Computation and Language · Computer Science 2023-12-12 Enes Altinisik , Hassan Sajjad , Husrev Taha Sencar , Safa Messaoud , Sanjay Chawla

Performing machine learning with analog signals offers advantages in speed and energy efficiency, but sensitivity to component and measurement imperfections often foils training without a system-specific companion digital model. Here we…

Disordered Systems and Neural Networks · Physics 2026-03-18 Sam Dillavou , Marcelo Guzman , Andrea J. Liu , Douglas J. Durian

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

Machine Learning · Computer Science 2023-06-14 Omar Montasser

Neural networks have changed the way machines interpret the world. At their core, they learn by following gradients, adjusting their parameters step by step until they identify the most discriminant patterns in the data. This process gives…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Samarup Bhattacharya , Anubhab Bhattacharya , Abir Chakraborty

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

Machine Learning · Computer Science 2025-09-24 Alexander Robey

Multimodal machine learning models that combine visual and textual data are increasingly being deployed in critical applications, raising significant safety and security concerns due to their vulnerability to adversarial attacks. This paper…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Maisha Binte Rashid , Pablo Rivas

Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few…

Machine Learning · Computer Science 2018-10-02 Anirban Chakraborty , Manaar Alam , Vishal Dey , Anupam Chattopadhyay , Debdeep Mukhopadhyay

Recent approaches in machine learning often solve a task using a composition of multiple models or agentic architectures. When targeting a composed system with adversarial attacks, it might not be computationally or informationally feasible…

Machine Learning · Computer Science 2024-11-01 Julian Collado , Kevin Stangl

Deep reinforcement learning has made significant progress in robotic manipulation tasks and it works well in the ideal disturbance-free environment. However, in a real-world environment, both internal and external disturbances are…

Robotics · Computer Science 2020-11-09 Pingcheng Jian , Chao Yang , Di Guo , Huaping Liu , Fuchun Sun

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Machine Learning · Computer Science 2022-02-03 Michael Everett , Bjorn Lutjens , Jonathan P. How

Neural ranking models (NRMs) have shown great success in information retrieval (IR). But their predictions can easily be manipulated using adversarial examples, which are crafted by adding imperceptible perturbations to legitimate…

Information Retrieval · Computer Science 2023-12-19 Yu-An Liu , Ruqing Zhang , Mingkun Zhang , Wei Chen , Maarten de Rijke , Jiafeng Guo , Xueqi Cheng

Artists are increasingly concerned about advancements in image generation models that can closely replicate their unique artistic styles. In response, several protection tools against style mimicry have been developed that incorporate small…

Cryptography and Security · Computer Science 2025-02-12 Robert Hönig , Javier Rando , Nicholas Carlini , Florian Tramèr

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Computation and Language · Computer Science 2022-10-28 Jiahao Zhao , Wenji Mao

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

Machine Learning · Computer Science 2021-07-27 Ali Rahmati , Seyed-Mohsen Moosavi-Dezfooli , Huaiyu Dai