paper-with-me

홈 › Papers

Risk Analysis and Design Against Adversarial Actions

2025-05-02 · Marco C. Campi, Algo Carè, Luis G. Crespo, Simone Garatti, Federico A. Ramponi

Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data encountered at deployment time often deviate from the conditions under which the model was trained. In this paper, we address deployment-time adversarial actions and propose a versatile, well-principled framework to evaluate the model's robustness against attacks of diverse types and intensities. While we initially focus on Support Vector Regression (SVR), the proposed approach extends naturally to the broad domain of learning via relaxed optimization techniques. Our results enable an assessment of the model vulnerability without requiring additional test data and operate in a distribution-free setup. These results not only provide a tool to enhance trust in the model's applicability but also aid in selecting among competing alternatives. Later in the paper, we show that our findings also offer useful insights for establishing new results within the out-of-distribution framework.

📄 PDF Abstract BibTeX arXiv:2505.01130

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks

2020-10-24 · Huimin Zeng, Chen Zhu, Tom Goldstein, Furong Huang

Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attac…

Adversarial Risk and the Dangers of Evaluating Against Weak Attacks

2018-02-15 · ICML 2018 7 · Jonathan Uesato, Brendan O'Donoghue, Aaron van den Oord, Pushmeet Kohli

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-c…

Adversarial Robustness

DECEPTICON: How Dark Patterns Manipulate Web Agents

2025-12-28 · Phil Cuvin, Hao Zhu, Diyi Yang arxiv

Deceptive UI designs, widely instantiated across the web and commonly known as dark patterns, manipulate users into performing actions misaligned with their goals. In this paper, we show that dark patterns are highly eff…

Attacking Autonomous Driving Agents with Adversarial Machine Learning: A Holistic Evaluation with the CARLA Leaderboard

2025-11-18 · Henry Wong, Clement Fung, Weiran Lin, Karen Li 외 arxiv

To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom modules. Although numerous prior works have shown that adversarial examples ca…

Autonomous Driving

Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks

2025-09-15 · Asim Waheed, Vasisht Duddu, Rui Zhang, Sebastian Szyller arxiv

Machine learning (ML) models are susceptible to various risks to security, privacy, and fairness. Most defenses are designed to protect against each risk individually (intended interactions) but can inadvertently affect …