English
Related papers

Related papers: Attack Selection Reduces Safety in Concentrated AI…

200 papers

The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, hindering the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression plays…

Artificial Intelligence · Computer Science 2024-01-03 Jie Zhu , Leye Wang , Xiao Han , Anmin Liu , Tao Xie

Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in…

Cryptography and Security · Computer Science 2022-11-03 Amira Guesmi , Ihsen Alouani , Khaled N. Khasawneh , Mouna Baklouti , Tarek Frikha , Mohamed Abid , Nael Abu-Ghazaleh

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…

Machine Learning · Computer Science 2025-04-15 Aryan Bhatt , Cody Rushing , Adam Kaufman , Tyler Tracy , Vasil Georgiev , David Matolcsi , Akbir Khan , Buck Shlegeris

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Cryptography and Security · Computer Science 2021-06-18 Giovanni Apruzzese , Mauro Andreolini , Luca Ferretti , Mirco Marchetti , Michele Colajanni

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

Cryptography and Security · Computer Science 2023-07-20 Alaa Khaddaj , Guillaume Leclerc , Aleksandar Makelov , Kristian Georgiev , Hadi Salman , Andrew Ilyas , Aleksander Madry

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Pengfei Xia , Ziqiang Li , Wei Zhang , Bin Li

Financial institutions face increasing cyber risk while operating under strict regulatory oversight. To manage this risk, they rely heavily on Cyber Threat Intelligence (CTI) to inform detection, response, and strategic security decisions.…

Cryptography and Security · Computer Science 2026-03-25 Emir Karaosman , Advije Rizvani , Irdin Pekaric

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this…

Machine Learning · Computer Science 2024-07-24 Ryan Greenblatt , Buck Shlegeris , Kshitij Sachan , Fabien Roger

AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catastrophic harm. Untrusted monitoring -- using one untrusted model to oversee another -- is one…

Despite the large body of academic work on machine learning security, little is known about the occurrence of attacks on machine learning systems in the wild. In this paper, we report on a quantitative study with 139 industrial…

Machine Learning · Computer Science 2023-03-13 Kathrin Grosse , Lukas Bieringer , Tarek Richard Besold , Battista Biggio , Katharina Krombholz

Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient. However, such systems are also at constant risk of being attacked. While the majority of attacks…

Human-Computer Interaction · Computer Science 2022-12-09 Benjamin Tag , Niels van Berkel , Sunny Verma , Benjamin Zi Hao Zhao , Shlomo Berkovsky , Dali Kaafar , Vassilis Kostakos , Olga Ohrimenko

Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting…

Robotics · Computer Science 2025-09-16 James C. Ward , Alex Bott , Connor York , Edmund R. Hunt

AI-based systems have been used widely across various industries for different decisions ranging from operational decisions to tactical and strategic ones in low- and high-stakes contexts. Gradually the weaknesses and issues of these…

Human-Computer Interaction · Computer Science 2022-01-13 Morteza Saberi

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Machine Learning · Computer Science 2022-05-03 Yang Li , Quan Pan , Erik Cambria

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Machine Learning · Computer Science 2024-07-17 Quang H. Nguyen , Nguyen Ngoc-Hieu , The-Anh Ta , Thanh Nguyen-Tang , Kok-Seng Wong , Hoang Thanh-Tung , Khoa D. Doan

Pattern classification systems are commonly used in adversarial applications, like biometric authentication, network intrusion detection, and spam filtering, in which data can be purposely manipulated by humans to undermine their operation.…

Machine Learning · Computer Science 2017-09-05 Battista Biggio , Giorgio Fumera , Fabio Roli

In distributed multiple-input multiple-output (D-MIMO) networks, power control is crucial to optimize the spectral efficiencies of users and max-min fairness (MMF) power control is a commonly used strategy as it satisfies uniform…

Signal Processing · Electrical Eng. & Systems 2023-01-24 Ömer Faruk Tuna , Fehmi Emre Kadan , Leyli Karaçay

Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we…

Cryptography and Security · Computer Science 2019-05-29 Jirong Yi , Hui Xie , Leixin Zhou , Xiaodong Wu , Weiyu Xu , Raghuraman Mudumbai

In this relatively informal discussion-paper we summarise issues in the domains of safety and security in machine learning that will affect industry sectors in the next five to ten years. Various products using neural network…

Cryptography and Security · Computer Science 2022-07-25 Hans Dermot Doran