English
Related papers

Related papers: Adversaries Can Misuse Combinations of Safe Models

200 papers

Humans are remarkably adept at collaboration, able to infer the strengths and weaknesses of new partners in order to work successfully towards shared goals. To build AI systems with this capability, we must first understand its building…

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

Cryptography and Security · Computer Science 2016-05-25 Nicolas Papernot , Patrick McDaniel , Ian Goodfellow

Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the…

Machine Learning · Computer Science 2018-11-27 Battista Biggio , Ignazio Pillai , Samuel Rota Bulò , Davide Ariu , Marcello Pelillo , Fabio Roli

Adversarial examples add imperceptible alterations to inputs with the objective to induce misclassification in machine learning models. They have been demonstrated to pose significant challenges in domains like image classification, with…

Cryptography and Security · Computer Science 2024-08-06 Muhammad Salman , Benjamin Zi Hao Zhao , Hassan Jameel Asghar , Muhammad Ikram , Sidharth Kaushik , Mohamed Ali Kaafar

While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data distributions. In this work, we introduce…

Computation and Language · Computer Science 2022-11-09 Saadia Gabriel , Hamid Palangi , Yejin Choi

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

Cryptography and Security · Computer Science 2026-01-12 Sahaya Jestus Lazer , Kshitiz Aryal , Maanak Gupta , Elisa Bertino

Completely Automated Public Turing test to tell Computers and Humans Apart, short for CAPTCHA, is an essential and relatively easy way to defend against malicious attacks implemented by bots. The security and usability trade-off limits the…

Cryptography and Security · Computer Science 2023-11-23 Zisheng Xu , Qiao Yan , F. Richard Yu , Victor C. M. Leung

Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging.…

Machine Learning · Computer Science 2023-09-15 Xinglong Chang , Katharina Dost , Kaiqi Zhao , Ambra Demontis , Fabio Roli , Gill Dobbie , Jörg Wicker

Deep learning models have been used for a wide variety of tasks. They are prevalent in computer vision, natural language processing, speech recognition, and other areas. While these models have worked well under many scenarios, it has been…

Machine Learning · Computer Science 2022-02-15 Daniel Steinberg , Paul Munro

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Cryptography and Security · Computer Science 2018-11-02 Luca Melis , Congzheng Song , Emiliano De Cristofaro , Vitaly Shmatikov

We address the problem of allocating limited resources in a network under persistent yet statistically unknown adversarial attacks. Each node in the network may be degraded, but not fully disabled, depending on its available defensive…

Data Structures and Algorithms · Computer Science 2025-07-01 Mansoor Davoodi , Setareh Maghsudi

Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…

Machine Learning · Computer Science 2024-01-08 Shorya Sharma

Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly…

Machine Learning · Computer Science 2017-06-16 Warren He , James Wei , Xinyun Chen , Nicholas Carlini , Dawn Song

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input…

Machine Learning · Computer Science 2018-07-10 Xiaoyong Yuan , Pan He , Qile Zhu , Xiaolin Li

AI companies are attempting to create AI systems that outperform humans at most economically valuable work. Current AI models are already automating away the livelihoods of some artists, actors, and writers. But there is infighting between…

Computers and Society · Computer Science 2023-12-20 Peter S. Park , Max Tegmark

Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…

Computer Vision and Pattern Recognition · Computer Science 2020-05-14 Ali Borji

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Yajie Wang , Shangbo Wu , Wenyi Jiang , Shengang Hao , Yu-an Tan , Quanxin Zhang

Neural networks are known to be vulnerable to adversarial examples: inputs that are close to natural inputs but classified incorrectly. In order to better understand the space of adversarial examples, we survey ten recent proposals that are…

Machine Learning · Computer Science 2017-11-02 Nicholas Carlini , David Wagner

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

Cryptography and Security · Computer Science 2018-12-04 Yujie Ji , Xinyang Zhang , Shouling Ji , Xiapu Luo , Ting Wang